Publication
Automatic Speech Recognition: A Comprehensive Guide Featuring Expert Perspectives
https://www.toptal.com/developers/whisper/automatic-speech-recognition-guide
Alessandro is available for hire
Hire AlessandroAlessandro Pedori
Verified Expert in Engineering
Artificial Intelligence Developer
Bologna, Metropolitan City of Bologna, Italy
Toptal member since November 18, 2022
Bio
Alessandro is a full-stack AI, NLP, and ML engineer, consultant, and architect with several years of experience teaching AIs what to do and building the code around it, mainly in Python. He also loves helping people understand the limits of current systems, triaging what to implement first, building code, teaching, consulting, mentoring, and coaching. Above all, Alessandro is passionate about how technology can empower humans to shine.
Portfolio
Epikast
Agentic AI, Agentic Frameworks, AI Chatbots, AI Design, AI Ethics...
IFS Collective
Agile Project Management, AI Design, Coaching, Psychology & Mental Health...
Hyper Island
Agile, University Teaching, Facilitation, Workshop Facilitation, Programming...
Experience
- Unix - 20 years
- Natural Language Processing (NLP) - 13 years
- Workshop Facilitation - 11 years
- Artificial Intelligence (AI) - 11 years
- Python - 11 years
- System Design - 11 years
- Technical Consulting - 6 years
- PyTorch - 5 years
Preferred Environment
MacOS, Linux, Python, Visual Studio Code (VS Code)
The most amazing...
...tool I've developed is a system to understand the intention of not renewing a subscription from client emails hinting to churn.
Work Experience
Lead AI Engineer | Lead of AI
2024 - PRESENT
Epikast
- Owned AI roadmap and execution for medical-affairs copilots and analytics; aligned research, product, and infra stakeholders.
- Defined evaluation, observability, and safety standards (traceability/auditability) for high-stakes workflows; enforced quality gates.
- Partnered with leadership on team growth (roles, hiring criteria, interviewing) and operating practices.
Technologies: Agentic AI, Agentic Frameworks, AI Chatbots, AI Design, AI Ethics, Medical Software, System Design, RAG Systems, RAG Pipelines, Agentic RAG Systems, Retrieval-augmented Generation (RAG), RAG Architecture, Pydantic, Neural Networks, Artificial Intelligence (AI), AI Adoption, AI Enablement
Co-founder | CTO | Coach
2022 - PRESENT
IFS Collective
- Co-created the offering of the company, shaping the goals and online presence.
- Envisioned, prepared, and facilitated online unconferences, adapting the software and tools to the online setting.
- Ideated, developed, and tested apps using AI to support IFS and other talk therapies.
Technologies: Agile Project Management, AI Design, Coaching, Psychology & Mental Health, Workshops, Workshop Facilitation, Facilitation, Healthcare, Health, Early-stage Startups, Healthcare IT, Generative Pre-trained Transformers (GPT), Generative Pre-trained Transformer 2 (GPT-2), DaVinci, OpenAI, Technical Leadership, Social Media, Chatbots, Conversational Interfaces, Large Language Models (LLMs), OpenAI GPT-3 API, Artificial General Intelligence (AGI), Hugging Face, Minimum Viable Product (MVP), Text-to-Speech (TTS), Automatic Speech Recognition (ASR), Speech-to-Text (STT), ChatGPT, Voice Recognition, Speaker Identification (SI), Generative Pre-trained Transformer 3 (GPT-3), Speech Synthesis, API Integration, Writing & Editing, Content Writing, AI Chatbots, Natural Language Toolkit (NLTK), Generative Artificial Intelligence (GenAI), LoRa, Training, Llama 3, Google Bard, LangChain, Sentiment Analysis, Retrieval-augmented Generation (RAG), LlamaIndex, Copywriting, Generative Pre-trained Transformer 4 (GPT-4), Machine Learning Algorithms, Pattern Recognition, AI Model Training, Agentic AI, Agentic Frameworks, Artificial Intelligence (AI), AI Adoption, AI Enablement, Coaching
Industry Leader | AI Business Consultant Course
2021 - PRESENT
Hyper Island
- Developed a curriculum that helps beginners get hands-on experience in programming and performing preliminary actions.
- Found, briefed, and coordinated workshop facilitators hosting lessons for the students.
- Triaged student ideas and developed projects with them.
Technologies: Agile, University Teaching, Facilitation, Workshop Facilitation, Programming, Python 3, Agile Project Management, Public Speaking, Communication, Open Source, AI Design, Visual Studio Code (VS Code), Consulting, Image Processing, Rapid Prototyping, Rapid Development, Rapid Application Development (RAD), Technical Consulting, Startup Consulting, Generative Pre-trained Transformers (GPT), Generative Pre-trained Transformer 2 (GPT-2), DaVinci, Artificial Intelligence (AI), Machine Learning, OpenAI, Cloud Platforms, Software Architecture, Technical Leadership, Social Media APIs, NLU, Deep Neural Networks (DNNs), Artificial General Intelligence (AGI), Hugging Face, Fine-tuning, Graphics Processing Unit (GPU), Minimum Viable Product (MVP), Speech-to-Text (STT), ChatGPT, Voice Recognition, Generative Pre-trained Transformer 3 (GPT-3), API Integration, Writing & Editing, Content Writing, Algorithms, Data Visualization, AI Chatbots, Generative Artificial Intelligence (GenAI), Data Scraping, PDF Scraping, Web Scraping, Workshops, Coaching, Training, Copywriting, Generative Pre-trained Transformer 4 (GPT-4), Artificial Neural Networks (ANN), Machine Learning Algorithms, AI Model Training, Neural Networks, Artificial Intelligence (AI), AI Adoption, AI Enablement, Coaching
Chief Technology Officer
2020 - PRESENT
EnterpriseAI Consulting UG
- Designed proof of concept and minimum viable products for several consulting projects, including requirements and implementation.
- Performed feasibility studies, triaged the required skills, set up and conducted necessary interviews, and performed high-level project management of the teams.
- Hosted workshops on data maturity and AI readiness for small and medium enterprises.
Technologies: Python 3, Scikit-learn, Pandas, PyTorch, Git, Agile, Workshops, Workshop Facilitation, APIs, Web Development, Architecture, Leadership, Communication, Open Source, Text Generation, Language Models, AI Design, Early-stage Startups, Startups, Visual Studio Code (VS Code), Programming, Consulting, Rapid Prototyping, Rapid Development, Rapid Application Development (RAD), Technical Consulting, Startup Consulting, Generative Pre-trained Transformers (GPT), Generative Pre-trained Transformer 2 (GPT-2), DaVinci, Text Processing, Artificial Intelligence (AI), Natural Language Processing (NLP), Machine Learning, OpenAI, PostgreSQL, Data Science, Cloud Platforms, Amazon Textract, Full-stack, Software Architecture, Technical Leadership, Social Media, Social Media APIs, NLU, Document Parsing, Test-driven Development (TDD), Deep Neural Networks (DNNs), NLPP, PDF, BERT, Conversational Interfaces, Text Recognition, Data Reporting, Data Analytics, Data Analysis, Amazon Lex, Large Language Models (LLMs), Data Processing, Data Transformation, CSV, Laravel, Automation, PHP, OpenAI GPT-3 API, Artificial General Intelligence (AGI), Hugging Face, Fine-tuning, Graphics Processing Unit (GPU), Minimum Viable Product (MVP), Text-to-Speech (TTS), Frameworks, Automatic Speech Recognition (ASR), XML, Speech-to-Text (STT), OpenAI GPT-4 API, ChatGPT, Voice Recognition, Amazon S3 (AWS S3), Speaker Identification (SI), AWS Step Functions, Generative Pre-trained Transformer 3 (GPT-3), Speech Synthesis, API Integration, Writing & Editing, Content Writing, Model Development, Algorithms, Data Matching, eCommerce, CSV File Processing, Inventory, Retail & Wholesale, Legal Technology (Legaltech), Insurance, Amazon, Data Visualization, Regression Modeling, Statistical Modeling, AI Chatbots, Natural Language Toolkit (NLTK), Custom Models, Topic Modeling, Generative Artificial Intelligence (GenAI), Text-to-text Transfer Transformer (T5), Data Scraping, PDF Scraping, Web Scraping, Data Engineering, Coaching, Training, Google Bard, Microsoft Copilot, LangChain, Sentiment Analysis, Google Speech API, Machine Learning Operations (MLOps), CI/CD Pipelines, Retrieval-augmented Generation (RAG), LlamaIndex, Copywriting, Generative Pre-trained Transformer 4 (GPT-4), Firebase, Electronic Health Records (EHR), Artificial Neural Networks (ANN), Graph Neural Networks (GNNs), Machine Learning Algorithms, Pattern Recognition, AI Model Training, Image Generation, Text to Image, Text to Image AI, Neural Networks, Artificial Intelligence (AI), AI Adoption, AI Enablement, Coaching
Senior P2P Interviewer for Data Science and Python Verticals
2020 - PRESENT
Job Board for Freelance Work
- Structured interviews for experienced Python programmers and created the curriculum for the data science vertical, including data scientists, data engineers, machine learning engineers, and data analysts.
- Interviewed 100+ candidates, from middle to CTO level, evaluating them on problem-solving, technical skills, and live coding.
- Developed proposals for live coding, allowing non-exerts to participate in technical interviews.
Technologies: Python, Scikit-learn, PyTorch, Keras, Statistics, Machine Learning, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), System Design, Interviewing, Team Management, Programming, Containerization, Communication, Data Science, Cloud Platforms, Software Architecture, NLU, Document Parsing, Deep Neural Networks (DNNs), Frameworks, Algorithms, Data Scraping, PDF Scraping, Web Scraping, Training, Machine Learning Algorithms, Artificial Intelligence (AI), AI Adoption, AI Enablement, Coaching
MVP Developer
2023 - 2023
Hearst - Technology
- Developed an app for Hearst media group to create full car listings from photos and replies to questions, using previous listings as models.
- Built an app to extract meaningful information from a list of devices to group them, using primarily LLMs, GPT, and heuristics.
- Developed an app to automate website scraping using a mixture of heuristic, NLP, and OpenAI APIs.
- Created an app to categorize car photos using zero shot pre-trained transformer models.
- Developed an app that scrapes and catalogs car data to create replies to questions to create car listings using OpenAI APIs.
Technologies: Python, Artificial General Intelligence (AGI), OpenAI GPT-3 API, Artificial Intelligence (AI), OpenAI GPT-4 API, Retrieval-augmented Generation (RAG), Chatbot Conversation Design, Svelte, Natural Language Processing (NLP), Algorithms, CSV File Processing, Azure, Amazon Bedrock AgentCore, Amazon, AI Chatbots, Custom Models, Topic Modeling, Generative Artificial Intelligence (GenAI), Text-to-text Transfer Transformer (T5), Data Scraping, PDF Scraping, Web Scraping, LangChain, ETL, Speech-to-Text (STT), Machine Learning Operations (MLOps), CI/CD Pipelines, LlamaIndex, Generative Pre-trained Transformer 4 (GPT-4), Large Language Model Operations (LLMOps), Artificial Neural Networks (ANN), Machine Learning Algorithms, Pattern Recognition, Agentic AI, Agentic Frameworks, Image Generation, Text to Image, Text to Image AI, Neural Networks, Artificial Intelligence (AI), AI Adoption, AI Enablement
Speaker Identification Model Consultant
2023 - 2023
GovWorx, Inc.
- Developed and fine-tuned language models to detect actions from transcriptions of interactions.
- Researched state-of-the-art developments for speaker identification, intent attribution, and summarization of long transcripts, then proposed implementations.
- Explored using available datasets and synthetic data for pre-launch development.
Technologies: PyTorch, Python, Voice Recognition, Amazon SageMaker, Amazon S3 (AWS S3), AWS Step Functions, Machine Learning, Speaker Identification (SI), Prompt Engineering, Natural Language Processing (NLP), Model Development, Amazon, AI Chatbots, Custom Models, Topic Modeling, Generative Artificial Intelligence (GenAI), LangChain, Speech-to-Text (STT), Retrieval-augmented Generation (RAG), LlamaIndex, Generative Pre-trained Transformer 4 (GPT-4), Artificial Neural Networks (ANN), Graph Neural Networks (GNNs), Machine Learning Algorithms, Pattern Recognition, Artificial Intelligence (AI), AI Enablement
Lead Research ML Engineer
2022 - 2022
molab.ai
- Developed and compared transformer-based models to predict molecule absorption, distribution, metabolism, excretion, and toxicity (ADMET) features from the simplified molecular-input line-entry system (SMILES) representation.
- Adapted published research code to the production environment.
- Created several data pipelines to test different models for ADMET prediction.
Technologies: Python, Scikit-learn, PyTorch, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Data Science, Cloud Platforms, NLU, Deep Neural Networks (DNNs), BERT, Large Language Models (LLMs), Data Processing, Data Transformation, CSV, Hugging Face, Fine-tuning, Graphics Processing Unit (GPU), API Integration, Model Development, Algorithms, CSV File Processing, Amazon, Data Visualization, Regression Modeling, Statistical Modeling, AI Chatbots, Custom Models, Data Engineering, ETL, CI/CD Pipelines, Generative Pre-trained Transformer 4 (GPT-4), Artificial Neural Networks (ANN), Machine Learning Algorithms, Pattern Recognition, AI Model Training, Neural Networks, Artificial Intelligence (AI), AI Adoption, AI Enablement
Senior ML Engineer
2021 - 2022
Ella Lab
- Took the models and software from proof of concept to deployment, having them react in the time required.
- Explored all possible ways to deploy huge transformer-based language models on available resources, working with bleeding edge architectures and constantly changing models.
- Oversaw the optimization and parallelization of the architecture, which resulted in a 10x reduction in the processing time.
- Deployed and tested big language model-based APIs in production, managing GPU out or memory errors and a continuously changing NLP system.
Technologies: Python, NVIDIA CUDA, PyTorch, Open Neural Network Exchange (ONNX), Docker, Google Cloud Platform (GCP), Agile, Git, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Parallel Programming, Distributed Software, Machine Learning Operations (MLOps), APIs, Web Development, Architecture, Leadership, Text Generation, Language Models, Google BigQuery, Data Pipelines, AI Design, Early-stage Startups, Startups, Visual Studio Code (VS Code), Programming, Rapid Prototyping, Rapid Development, Rapid Application Development (RAD), Text Processing, Artificial Intelligence (AI), Machine Learning, PostgreSQL, Data Science, Cloud Platforms, Full-stack, Software Architecture, Technical Leadership, Social Media, NLU, Test-driven Development (TDD), Deep Neural Networks (DNNs), BERT, Conversational Interfaces, Google Cloud, Google Cloud Datastore, Google AI Platform, Google Cloud ML, Large Language Models (LLMs), Data Processing, Data Transformation, CSV, Automation, Artificial General Intelligence (AGI), Hugging Face, Fine-tuning, Graphics Processing Unit (GPU), Minimum Viable Product (MVP), Frameworks, Automatic Speech Recognition (ASR), AWS Step Functions, Generative Pre-trained Transformer 3 (GPT-3), API Integration, Model Development, Algorithms, CSV File Processing, AI Chatbots, Natural Language Toolkit (NLTK), Custom Models, Generative Artificial Intelligence (GenAI), Text-to-text Transfer Transformer (T5), Web Scraping, Data Engineering, Sentiment Analysis, ETL, CI/CD Pipelines, Generative Pre-trained Transformer 4 (GPT-4), Large Language Model Operations (LLMOps), Artificial Neural Networks (ANN), Machine Learning Algorithms, Pattern Recognition, AI Model Training, Neural Networks, Artificial Intelligence (AI), AI Adoption, AI Enablement
Chief Data Scientist
2021 - 2022
Staircase
- Implemented ways to extract behavior from customer emails, differentiating general emotions from the intention not to renew contracts or services.
- Developed ways to extract company information from emails, calendar invites, and meeting transcriptions. The extracted data included the role of different people, their capacity to influence decisions, and changes in their roles.
- Oversaw design and re-implementation of several services, including traditional NLP, regular expressions, transformers, and deep learning.
- Supported the transition to using and deploying transformers for NLP in production.
- Consulted on appropriate technological solutions and feasibility.
Technologies: Python 3, PyTorch, Agile, Git, DevOps, Scikit-learn, Regex, Unix, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), APIs, Architecture, Leadership, Text Generation, Language Models, Data Pipelines, AI Design, Early-stage Startups, Startups, Visual Studio Code (VS Code), Programming, Consulting, Rapid Prototyping, Rapid Development, Rapid Application Development (RAD), Text Processing, Artificial Intelligence (AI), Machine Learning, OpenAI, Data Science, Cloud Platforms, Technical Leadership, NLU, Document Parsing, Test-driven Development (TDD), Deep Neural Networks (DNNs), NLPP, PDF, BERT, Chatbots, Conversational Interfaces, Text Recognition, Data Reporting, Data Analytics, Data Analysis, Large Language Models (LLMs), Data Processing, Data Transformation, CSV, Automation, Artificial General Intelligence (AGI), Hugging Face, Fine-tuning, Graphics Processing Unit (GPU), Minimum Viable Product (MVP), Text-to-Speech (TTS), Frameworks, Automatic Speech Recognition (ASR), Amazon S3 (AWS S3), AWS Step Functions, Generative Pre-trained Transformer 3 (GPT-3), API Integration, Model Development, Algorithms, eCommerce, CSV File Processing, Amazon, Data Visualization, Regression Modeling, Statistical Modeling, AI Chatbots, Natural Language Toolkit (NLTK), Custom Models, Topic Modeling, Generative Artificial Intelligence (GenAI), Text-to-text Transfer Transformer (T5), Data Scraping, PDF Scraping, Web Scraping, Data Engineering, Training, Sentiment Analysis, ETL, Speech-to-Text (STT), Machine Learning Operations (MLOps), CI/CD Pipelines, Large Language Model Operations (LLMOps), Artificial Neural Networks (ANN), Graph Neural Networks (GNNs), Machine Learning Algorithms, Pattern Recognition, AI Model Training, Neural Networks, AI Adoption, AI Enablement
Lead ML Engineer
2020 - 2020
Klarna
- Developed MLOps systems with very low latence to maintain high availability under high loads.
- Evaluated several platforms to enable data scientists to deploy models without involving engineers (hint: not recommended).
- Created several proofs of concept for ML and DS process improvements.
Technologies: Python 3, Scikit-learn, Amazon SageMaker, Amazon Web Services (AWS), Git, AI Design, Startups, Visual Studio Code (VS Code), Programming, SQL, Artificial Intelligence (AI), Machine Learning, Cloud Platforms, Software Architecture, Technical Leadership, Test-driven Development (TDD), Deep Neural Networks (DNNs), Data Processing, Data Transformation, AWS Step Functions, Algorithms, CSV File Processing, Retail & Wholesale, Data Engineering, ETL, CI/CD Pipelines, Artificial Neural Networks (ANN), Machine Learning Algorithms, AI Adoption, AI Enablement
Senior ML Engineer
2019 - 2020
Miele
- Designed and built microservices architecture serving different ML models for shape recognition, categorization, text detection with subsequent OCR, etc.
- Set up DevOps architecture for other developers and remote access.
- Oversaw the curation of image data, the selection of text detection, optimization and recognition algorithms, and object recognition.
Technologies: Python 3, Keras, OpenCV, Git, Linux, Ubuntu, TensorFlow, Machine Learning, Computer Vision, Optical Character Recognition (OCR), Web Development, Architecture, AI Design, Visual Studio Code (VS Code), Programming, Image Processing, Rapid Prototyping, Rapid Development, Rapid Application Development (RAD), Artificial Intelligence (AI), Data Science, Software Architecture, NLU, Document Parsing, Test-driven Development (TDD), Deep Neural Networks (DNNs), Text Recognition, Graphics Processing Unit (GPU), Minimum Viable Product (MVP), Frameworks, Model Development, CSV File Processing, Data Visualization, Custom Models, Web Scraping, ETL, CI/CD Pipelines, Artificial Neural Networks (ANN), Machine Learning Algorithms, Pattern Recognition, AI Model Training, Neural Networks, AI Adoption, AI Enablement
Senior NLP Engineer
2018 - 2019
Retresco
- Extracted and organized gigabytes of data from Wikidata, restructuring the process to parallelize and speed up from more than two days to less than four hours.
- Implemented NLP processes to disambiguate pieces of information from Wikidata, creating an IBM Watson-like system to answer general knowledge queries.
- Restructured the architecture of a complex system already in deployment, allowing a better evolution of the platform and bug fixing.
Technologies: Elasticsearch, Python 3, Wikidata, Tornado, Git, APIs, Speech Recognition, Web Development, Architecture, Text Generation, Language Models, Data Pipelines, AI Design, Startups, Voice Analysis, Visual Studio Code (VS Code), Programming, SQL, Rapid Development, Rapid Application Development (RAD), Text Processing, Artificial Intelligence (AI), Machine Learning, PostgreSQL, Data Science, Cloud Platforms, Software Architecture, Technical Leadership, Social Media, Social Media APIs, NLU, Deep Neural Networks (DNNs), BERT, Chatbots, Conversational Interfaces, Text Recognition, Data Processing, Data Transformation, CSV, Minimum Viable Product (MVP), Frameworks, API Integration, Data Matching, eCommerce, CSV File Processing, Retail & Wholesale, Data Visualization, AI Chatbots, Natural Language Toolkit (NLTK), Custom Models, Topic Modeling, Web Scraping, Data Engineering, Sentiment Analysis, ETL, CI/CD Pipelines, Machine Learning Algorithms, AI Adoption, AI Enablement
Research Engineer in NLP and ML
2016 - 2017
Aaron
- Applied NLP and ML techniques to automate customer support tasks.
- Performed data analysis, clean-up, normalization, and topic modeling on business and customer support data.
- Designed and implemented Alexa skills-based voice assistants for financial services, including checking account balances and blocking and requesting credit cards.
Technologies: Python 3, Amazon Alexa, Amazon Web Services (AWS), Scikit-learn, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Speech Recognition, Web Development, Architecture, JavaScript, Text Generation, AI Design, Early-stage Startups, Startups, Voice Analysis, Programming, Consulting, SQL, Rapid Prototyping, Rapid Development, Rapid Application Development (RAD), Text Processing, Artificial Intelligence (AI), Machine Learning, Data Science, Cloud Platforms, Full-stack, Software Architecture, NLU, Document Parsing, Deep Neural Networks (DNNs), Dialogflow, Conversational Interfaces, Text Recognition, Data Reporting, Data Analytics, Data Analysis, CSV, Minimum Viable Product (MVP), Frameworks, Voice Recognition, gRPC, Model Development, Data Matching, CSV File Processing, Data Visualization, Statistical Modeling, AI Chatbots, Natural Language Toolkit (NLTK), Custom Models, Data Engineering, ETL, Artificial Neural Networks (ANN), Machine Learning Algorithms, Neural Networks, AI Enablement
Senior Python Back-end Developer
2015 - 2016
UberResearch
- Developed ways to parallelize the code using ZeroMQ, cutting the execution time from days to hours.
- Oversaw the code development required to ingest several gigabytes of data in the system, keeping it up to date on AWS without replications.
- Planned, designed, implemented, and refined ETL pipelines for the data processes.
Technologies: Python, Scikit-learn, ZeroMQ, Pyramid, Flask, Unix, MacOS, Web Development, Architecture, JavaScript, Data Pipelines, Healthcare, Health, Early-stage Startups, Startups, Healthcare IT, Programming, SQL, Rapid Prototyping, Rapid Development, Rapid Application Development (RAD), PostgreSQL, Cloud Platforms, Full-stack, Software Architecture, Technical Leadership, Document Parsing, PDF, Data Reporting, Data Analytics, Data Analysis, Data Processing, Data Transformation, CSV, Frameworks, gRPC, Data Engineering, ETL, Machine Learning Algorithms
Support and Sales Engineer
2013 - 2015
Acrolinx
- Developed an app to collect user feedback on the support team via simple links in emails (a the time, it was new) and visualized it on a dynamic page on the company website.
- Tracked and fixed bugs, supporting customers in adapting the software provided to their needs.
- Expanded the language capabilities of the software to support the different needs of clients.
Technologies: Java, Python, IT Support, Email Support, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Windows, Text Processing, PDF, PHP, gRPC
Senior Localization Engineer for Siri
2012 - 2012
Apple
- Implemented ways to adapt Siri's expressions to Italian for its first international release.
- Kept track of bug priorities and coordinated with translators, testers, and other engineers.
- Oversaw the triaging and fixing of important edge cases, including pre-empting ways in which users would try to get Siri to be vulgar or inappropriate.
Technologies: Artificial Intelligence (AI), Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Git, Siri, Speech Recognition, Text Generation, Programming, Text Processing, NLU, Chatbots, Conversational Interfaces, Speech-to-Text (STT), Voice Recognition, AI Chatbots
Localization Engineer
2011 - 2012
Snap-On
- Built a tool to automate daily localization checks, going from a two-hour daily workload to a five-hour one.
- Downloaded, compared, and checked 16+ million words of localized content regularly, coordinating with translators and engineers.
- Developed a system to compare inventory items between departments, scraping inventory websites and connecting databases.
Technologies: Python, Perl, MacOS, Localization, Localization Testing, Text Processing, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), PDF, PHP, Writing & Editing
Experience
General Intent Detection from Customers' Emails
This project involved the creation of a Python-based system that used natural language inference (NLI) to identify emails signaling a lack of satisfaction from customers, hinting at churn. The system was able, for example, to differentiate between overall dissatisfaction from dissatisfaction with the service and the user leaving the company from the user leaving the service.
I was the main back-end developer. I also developed the algorithms based on NLI transformer models and some additional custom rules. The customer was so happy with the system they decided to apply to patent the technique; if accepted, my name would be on the patent.
I was the main back-end developer. I also developed the algorithms based on NLI transformer models and some additional custom rules. The customer was so happy with the system they decided to apply to patent the technique; if accepted, my name would be on the patent.
Voice-activated Shopping Based on Alexa
This project involved creating a Python-based NLP-powered Alexa skill to allow users to shop via voice. We extracted the information from the inventory, structured a flow so that the user would be presented with only a little information, and debugged the glitches introduced by the Alexa platform.
I was the main designer, back-end developer, NLP developer, and interaction designer. This tool was created in 2018, when the ideal use of voice-activated assistants was unclear. The project was a tremendous technical success and proved that users did not want to shop for groceries talking to Alexa.
I was the main designer, back-end developer, NLP developer, and interaction designer. This tool was created in 2018, when the ideal use of voice-activated assistants was unclear. The project was a tremendous technical success and proved that users did not want to shop for groceries talking to Alexa.
Telegram Voice Messages Transcription Bot
I created a Python- and Telegram-based bot to transcribe voice messages using state-of-the-art voice recognition transformer models. I designed different interaction UXs and implemented possible monetization paths.
Gender B(l)ender
A Python and JavaScript-based NLP web app to visualize and neutralize gender bias in the text. Using spaCy and other NLP technologies, it would identify gendered language and neutralize it (using singular or plural "they" or a pronoun of choice), randomly mix it, or invert it. Developed as a personal curiosity about the prevalence of bias in text and how to properly use neutral/gender-free pronouns (this was 2015, and it was new).
Adding German Support to LangCheck
https://github.com/ischender/langcheckExtended a library for checking the output of LLMs to German, plus added some multilingual content. Researched and tested the models, expanded the code, created and controlled tests, and prepared new data sets.
Education
1995 - 2004
Master's Degree in Computer Engineering
University of Bologna - Bologna, Italy
Skills
Libraries/APIs
PyTorch, Scikit-learn, Social Media APIs, Natural Language Toolkit (NLTK), ZeroMQ, Keras, OpenCV, TensorFlow, Telegram Messenger API, Pandas, SpaCy, Google Speech API, Pydantic
Tools
ChatGPT, Git, Google AI Platform, Google Bard, Microsoft Copilot, Open Neural Network Exchange (ONNX), Amazon SageMaker, Amazon Textract, NLPP, Dialogflow, Amazon Lex, AWS Step Functions, Whisper
Languages
Python, Elixir, SQL, Python 3, Regex, JavaScript, Perl, Java, HTML, PHP, XML
Paradigms
Agile, Rapid Prototyping, Rapid Application Development (RAD), Automation, Test-driven Development (TDD), ETL, DevOps, Parallel Programming, Agile Project Management
Platforms
MacOS, Visual Studio Code (VS Code), Unix, Linux, Google Cloud Platform (GCP), Amazon Web Services (AWS), Amazon, Amazon Alexa, Docker, NVIDIA CUDA, Ubuntu, Windows, Heroku, Azure, Firebase
Frameworks
Flask, Pyramid, Bootstrap, Laravel, gRPC, Svelte, LlamaIndex, Agentic Frameworks
Storage
Data Pipelines, Elasticsearch, PostgreSQL, Google Cloud, Google Cloud Datastore, Amazon S3 (AWS S3)
Industry Expertise
Healthcare, Social Media, Retail & Wholesale, Insurance
Other
Programming, Artificial Intelligence (AI), Natural Language Processing (NLP), Consulting, Technical Consulting, Workshop Facilitation, Machine Learning, Chatbots, Workshops, APIs, Rapid Development, Communication, Text Generation, Language Models, AI Design, Early-stage Startups, Startups, Coaching, Generative Pre-trained Transformers (GPT), Generative Pre-trained Transformer 2 (GPT-2), Text Processing, Software Architecture, Technical Leadership, NLU, Document Parsing, Deep Neural Networks (DNNs), BERT, Conversational Interfaces, Text Recognition, Large Language Models (LLMs), Data Processing, Data Transformation, CSV, OpenAI GPT-3 API, Artificial General Intelligence (AGI), Hugging Face, Fine-tuning, Minimum Viable Product (MVP), Generative Pre-trained Transformer 3 (GPT-3), API Integration, Writing & Editing, Model Development, Algorithms, CSV File Processing, AI Chatbots, Custom Models, Generative Artificial Intelligence (GenAI), Text-to-text Transfer Transformer (T5), Data Scraping, PDF Scraping, Web Scraping, Training, Sentiment Analysis, Generative Pre-trained Transformer 4 (GPT-4), Artificial Neural Networks (ANN), Machine Learning Algorithms, Pattern Recognition, Artificial Intelligence (AI), AI Adoption, AI Enablement, System Design, Startup Consulting, Public Speaking, Interviewing, Deep Learning, Machine Learning Operations (MLOps), Optical Character Recognition (OCR), Speech Recognition, Architecture, Leadership, Open Source, Health, Voice Analysis, OpenAI, Data Science, Cloud Platforms, Full-stack, PDF, Data Analytics, Data Analysis, Text-to-Speech (TTS), Frameworks, Speech-to-Text (STT), OpenAI GPT-4 API, Voice Recognition, Speech Synthesis, Content Writing, Data Matching, Topic Modeling, Data Engineering, Llama 3, LangChain, CI/CD Pipelines, Copywriting, Large Language Model Operations (LLMOps), AI Model Training, Agentic AI, Neural Networks, Coaching, Networking, Siri, Statistics, Team Management, Containerization, User Experience (UX), Voice, Distributed Software, University Teaching, Facilitation, Wikidata, Tornado, Computer Vision, Telegram Bots, Image Processing, Web Development, Plugins, Google BigQuery, Healthcare IT, Psychology & Mental Health, DaVinci, Localization, Localization Testing, IT Support, Email Support, Google Cloud ML, Data Reporting, Graphics Processing Unit (GPU), Automatic Speech Recognition (ASR), Speaker Identification (SI), Prompt Engineering, Retrieval-augmented Generation (RAG), Chatbot Conversation Design, eCommerce, Inventory, Amazon Bedrock AgentCore, Legal Technology (Legaltech), Data Visualization, Regression Modeling, Statistical Modeling, LoRa, Electronic Health Records (EHR), Graph Neural Networks (GNNs), Image Generation, Text to Image, Text to Image AI, AI Ethics, Medical Software, RAG Systems, RAG Pipelines, Agentic RAG Systems, RAG Architecture
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring