Eduard is available for hire
Hire EduardEduard Mihranyan
Verified Expert in Engineering
Machine Learning Developer
Yerevan, Armenia
Toptal member since January 10, 2022
Bio
Eduard is a highly accomplished data scientist with nine years of experience spanning the IT, banking, healthcare, and insurance industries. Known for delivering high-impact, end-to-end data solutions that drive measurable improvements in business KPIs, he has built a strong reputation as a strategic problem solver. In recent years, Eduard has focused on generative AI, LLMs, and data engineering, continuously staying ahead of emerging technologies to enhance his expertise.
Portfolio
ServiceTitan
Azure, Large Language Models (LLMs), OpenAI, Software Engineering...
SumerSports, LLC - Main
Databricks, Kubernetes, Python, Data Processing, PySpark, Apache Airflow...
ContractPod Technologies Limited
Natural Language Processing (NLP), Data Science, LSTM, Machine Learning...
Experience
- Python - 9 years
- Machine Learning - 9 years
- Deep Learning - 9 years
- Data Analysis - 9 years
- Scikit-learn - 7 years
- Recommendation Systems - 6 years
- PySpark - 5 years
- Large Language Models (LLMs) - 4 years
Preferred Environment
PyCharm, Slack, GitHub, Amazon Web Services (AWS), JupyterLab, Azure ML Studio, OpenAI GPT-4 API
The most amazing...
...project I've led was developing a car insurance model that is now adopted by most insurance companies in my country, reshaping risk assessment and pricing.
Work Experience
Senior AI Engineer
2024 - PRESENT
ServiceTitan
- Developed an automated model to score customer service representatives' performance, streamlining evaluation processes and enhancing the efficiency of performance assessments.
- Created a model to generate short audio briefs, providing technicians with relevant information to prepare them for customer house visits, improving service quality, and increasing sales during customer interactions.
- Contributed to the development of a voicebot that interacts with customers, collects necessary information, and books jobs, enhancing the customer experience and automating service scheduling.
Technologies: Azure, Large Language Models (LLMs), OpenAI, Software Engineering, Machine Learning, Retrieval-augmented Generation (RAG), Hugging Face Transformers, Statistical Modeling, Speech-to-Text (STT), Cloud, Real-time Systems, Fine-tuning, Machine Learning Operations (MLOps), Data Visualization, Dashboards, Dashboard Design
Data Engineer
2024 - 2024
SumerSports, LLC - Main
- Implemented a medallion architecture, organizing data into bronze, silver, and gold layers in Databricks, which improved data quality, accessibility, and performance for analytics workflows.
- Set up automated data pipelines in Databricks, streamlining data processing workflows and ensuring efficient data ingestion, transformation, and storage.
- Implemented data migration workflows using Airflow, ensuring smooth and timely data transfer between different environments while enhancing the overall data pipeline efficiency and reliability.
- Collaborated with the team to optimize performance and troubleshoot data engineering issues, contributing to a more stable and efficient data environment that supported real-time analytics and insights for the company.
Technologies: Databricks, Kubernetes, Python, Data Processing, PySpark, Apache Airflow, Data Pipelines, Medallion Architecture, Hugging Face Transformers, Statistical Modeling, Cloud, Data Visualization, Dashboards, Dashboard Design
Data Scientist/ML Engineer
2023 - 2024
ContractPod Technologies Limited
- Contributed to the development of an information extraction pipeline, helping identify key clauses and terms within legal contracts, enabling the system to summarize important content effectively for further analysis.
- Assisted in fine-tuning a large language model (LLM) using reinforcement learning with human feedback (RLHF) to enhance its ability to interpret complex legal language and accurately answer contract-related questions.
- Worked closely with legal experts to gather feedback and refine the model’s performance, ensuring it could provide contextually relevant answers to user queries and improve the efficiency of contract review processes.
Technologies: Natural Language Processing (NLP), Data Science, LSTM, Machine Learning, TensorFlow, BERT, Python, OpenAI, Llama 2, Reinforcement Learning, Large Language Models (LLMs), Language Models, ChatGPT, Falcon, PEFT, Reinforcement Learning from Human Feedback (RLHF), Retrieval-augmented Generation (RAG), Hugging Face Transformers, Statistical Modeling, Cloud, Fine-tuning, Data Visualization, Dashboards, Dashboard Design
Lead Machine Learning Engineer
2022 - 2024
Plat.AI
- Created an object replacement model, which finds the described object in the image and replaces it with the provided image of the new object, keeping everything else the same.
- Fine-tuned an instruction-based LLM to solve a specific summarization task for the company data.
- Developed a reinforcement learning environment to explore and distribute resources optimally, maximizing the company's profit. The project had the highest priority and showed significant improvements.
- Designed an insurance scoring model, which estimates the probability of accidents and calculates the insurance rate based on the risk.
- Built a customer time series prediction model to be used in the banking industry for improving their scoring models.
Technologies: Text to Image, Analytics, Machine Learning, Deep Learning, Finance, Python, OpenAI GPT-3 API, Language Models, Reinforcement Learning, Amazon Web Services (AWS), Generative Pre-trained Transformer 3 (GPT-3), Generative Pre-trained Transformers (GPT), OpenAI GPT-4 API, Predictive Modeling, Pricing Models, Git, Docker, Data Scientist, ChatGPT, OpenAI, Azure, Azure SQL Data Warehouse, Dedicated SQL Pool (formerly SQL DW), Google Cloud Platform (GCP), SQL, Large Language Models (LLMs), Data Processing, Kubernetes, Feature Engineering, Prompt Engineering, Retrieval-augmented Generation (RAG), Hugging Face Transformers, Statistical Modeling, Speech-to-Text (STT), Cloud, Real-time Systems, Fine-tuning, Machine Learning Operations (MLOps), Data Visualization
Machine Learning Engineer
2023 - 2023
Polarity Labs, LLC
- Played a key role in launching the live version of the similar book recommendation feature.
- Built the foundational framework for the recommendation system, focusing on collecting and preprocessing data for books and places.
- Assisted in developing a collaborative filtering algorithm, which would help personalize recommendations based on user interactions when sufficient user data is collected.
Technologies: Machine Learning, Recommendation Systems, Artificial Intelligence (AI), Startups, Early-stage Startups, Hugging Face Transformers, Statistical Modeling, Cloud, Real-time Systems, Data Visualization, Dashboards
Google Recommendation AI Specialist
2022 - 2022
The Estee Lauder Companies Inc.
- Developed an automated recommendation pipeline that collects and preprocesses data, trains a model, and serves as an API endpoint to request and get recommendations.
- Designed a comprehensive A/B test for checking the recommendation model's online performance.
- Created and trained in-house recommendation models—user-based and item-based—which may be used to replace the current solution in the future.
Technologies: Artificial Intelligence (AI), Google AI Platform, Recommendation Systems, Google, Python, Machine Learning, APIs, Google BigQuery, AI Design, Neural Networks, Forecasting, MySQL, Data Pipelines, Snowflake, Model Development, Data Analytics, Data Extraction, Data Engineering, Git, Data Scientist, Google Cloud Platform (GCP), Google Analytics, BigQuery, Data Processing, Real-time Systems, Dashboards
Full-stack Machine Learning Scientist
2019 - 2022
PicsArt
- Built an in-house text-to-image generation model based on Stable Diffusion, which works live, and an integrated fine-tuning mechanism so the generator could create and modify users' pictures, e.g., create a superhero with your face.
- Developed recommender system models for sticker recommendations to a user. The first model was based on user preferences and has shown more than 300% growth in sticker usage in each touchpoint when rolled out.
- Grew premium content usage by 150% and saw a significant increase in subscription metrics after creating a model that considers the visual match between a photo and sticker used for cold-start users and premium stickers.
- Boosted the marketing team's campaign success rates in targeting audiences by designing a model that captures user preferences toward PicsArt tools and content and divides them into meaningful segments.
- Created an anomaly detection algorithm that captures anomalous spikes in app crashes and reports them to the development team, improving the team's process for fixing bugs.
- Increased the company's revenue significantly by developing an ads optimization model that showed users ads and subscription offer screens.
- Conducted a global company analysis for the CEO to find optimal ways of development, which changed the company's growth direction and resulted in a new department organized with the highest priority projects.
- Managed a team of three members working on different projects and encouraged their personal growth.
Technologies: Machine Learning, Deep Learning, Data Analysis, Engineering, CI/CD Pipelines, Torch, Reinforcement Learning, Statistics, Research, Python, PySpark, Pandas, Scikit-learn, Gensim, NumPy, Artificial Intelligence (AI), Recommendation Systems, GitHub, Data Science, Google AI Platform, Mathematics, Analytics, Time Series, R, APIs, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), AI Design, Time Series Analysis, Amazon Web Services (AWS), Neural Networks, Artificial Neural Networks (ANN), TensorFlow, Image Generation, ARIMA, Forecasting, LSTM, Natural Language Understanding (NLU), PyTorch, JupyterLab, MySQL, Random Forests, XGBoost, Data Pipelines, Linear Regression, Snowflake, Model Development, Keras, Computer Vision, BERT, Data Analytics, Data Reporting, Language Models, Data Extraction, Data Engineering, Predictive Modeling, Predictive Analytics, Databricks, Azure Databricks, Data-driven Marketing, Pricing Models, Git, Docker, Algorithms, Data Scientist, PostgreSQL, Plotly, Tableau, Data Manipulation, Data Modeling, OpenAI, Azure, Dedicated SQL Pool (formerly SQL DW), Azure SQL Data Warehouse, Google Cloud Platform (GCP), Statistical Data Analysis, SQL, Google Analytics, BigQuery, Transformers, Data Processing, Kubernetes, Feature Engineering, Hugging Face Transformers, Statistical Modeling, Real-time Systems, Social Networks, Search, Dashboards
Machine Learning Scientist
2018 - 2019
Ameriabank
- Developed a credit risk model to predict defaults of retained clients that currently works as the primary method for landing retail credits. The result is a significant increase in the company's profit.
- Created a model to predict the risk of corporate clients as the primary method for landing corporate credits, which resulted in a significant increase in the company's profit.
- Developed a credit portfolio optimization model to increase the profitability of the current portfolio.
Technologies: Machine Learning, Deep Learning, Finance, Data Analysis, Optimization, Python, Pandas, Torch, Scikit-learn, Gensim, NumPy, Artificial Intelligence (AI), GitHub, Data Science, Mathematics, Analytics, Time Series, R, APIs, AI Design, Architecture, Time Series Analysis, Amazon Web Services (AWS), Microsoft Power BI, Neural Networks, Artificial Neural Networks (ANN), TensorFlow, AI Programming, ARIMA, Forecasting, LSTM, Natural Language Understanding (NLU), PyTorch, JupyterLab, MySQL, Random Forests, XGBoost, Data Pipelines, Linear Regression, Model Development, Keras, Computer Vision, BERT, Data Analytics, Data Reporting, Language Models, Data Extraction, Predictive Modeling, Predictive Analytics, Data-driven Marketing, Git, Algorithms, Data Scientist, PostgreSQL, Tableau, Data Manipulation, Financial Analysis, Statistical Data Analysis, SQL, Feature Engineering, Statistical Modeling, Real-time Systems
Machine Learning Engineer
2017 - 2018
BetConstruct
- Improved the previous prototype for modeling the final score of soccer matches.
- Developed a model that predicted corner kicks and the number of yellow or red cards in a soccer match.
- Created a model to predict the final result of a basketball match—win, loss, or tie.
Technologies: Machine Learning, Deep Learning, Gaming, Python, Pandas, Data Analysis, Scikit-learn, NumPy, Artificial Intelligence (AI), GitHub, Data Science, Mathematics, Analytics, Time Series, R, AI Design, Microsoft Power BI, Neural Networks, Artificial Neural Networks (ANN), TensorFlow, AI Programming, Forecasting, LSTM, Natural Language Understanding (NLU), PyTorch, JupyterLab, MySQL, Random Forests, XGBoost, Linear Regression, Model Development, Keras, Computer Vision, BERT, Data Analytics, Data Reporting, Data Extraction, Predictive Modeling, Algorithms, Data Scientist, Google Analytics, Feature Engineering, Statistical Modeling
Data Scientist
2016 - 2017
TeamViewer Germany
- Collaborated with the growth hackers team and analyzed the main direction of the company's growth; found out optimal bundling of current products and optimal prices for sales.
- Conducted churn analysis based on comments from past users, which led to the main reasons for client churn (text analysis).
- Created analytic dashboards for monitoring company-wide metrics.
Technologies: Machine Learning, Statistics, Data Analysis, SQL, R, Pandas, Scikit-learn, NumPy, Data Science, Mathematics, Analytics, Time Series, AI Design, Time Series Analysis, Microsoft Power BI, Neural Networks, Artificial Neural Networks (ANN), AI Programming, ARIMA, Forecasting, JupyterLab, Random Forests, XGBoost, Linear Regression, BERT, Data Analytics, Data Reporting, Predictive Analytics, Data-driven Marketing, Algorithms, Data Scientist, Tableau, Google Analytics
Experience
Legal Context-aware LLM Development
I've collaborated on the development of a legal context-aware LLM model. The model should be able to summarize legal documents, extract necessary information from long legal texts, understand the legal context, and answer questions regarding a given document. RLHF training on human-annotated data helped achieve the desired results.
Building a Medallion Architecture Data Platform on Databricks
The project involved setting up an end-to-end data engineering solution using Databricks on Azure. We implemented a Medallion Architecture (Bronze, Silver, Gold layers) to systematically ingest, clean, and prepare data from multiple disparate sources for advanced analytics and machine learning initiatives.
Building a Customer Support Quality Measurement Model
The goal of the project was to develop a system that automatically assesses customer support representatives' (CSRs) call performance based on predefined communication guidelines. The solution processes monthly call data to evaluate specific quality criteria, aggregate scores per call and per CSR, and produce a final quality rating.
Building an Intelligent VoiceBot for Home Service Job Booking
The project aimed to design and implement an AI-driven VoiceBot that could autonomously handle customer calls, gather necessary information, validate input, understand service needs, and book appointments on a home services platform—all without human intervention.
Text to Image Generator
A Stable Diffusion-based model is trained to create images using Gaussian noise while taking user-provided guidance in the form of images and text. By giving the model a user's photo and accompanying text instructions, the generator can produce a new image that modifies the original photo according to the given instructions. For example, it can create a superhero image with the user's face and position the superhero near the Eiffel Tower.
Recommendation System for a New App
Developed a recommendation algorithm for a new application without user data, where the goal was to generate "you might also be interested in" type of recommendations for books, movies, and places. We've managed to deploy it to production in quite a short period and to monitor user's interactions with recommended items.
Preference-based Recommender System
The model captured user-to-item and item-to-item interactions to predict and recommend new items to the current users. We trained the model on vast data of PicsArt users and their usage of stickers. Currently, the model is in production on all platforms and touchpoints.
Photo-based Recommender System
The model captured the best fit between photos and stickers based on previously selected, excellent quality photo edits. It used a metric learning approach to obtain the distance between a photo and sticker based on their visual characteristics.
Marketing Campaign Optimization
My role in this project was to create a machine learning model that discovered users' interests toward features of the application and divided all users into subgroups with similar interests. The marketing team used this to run the targeted marketing campaigns on the smaller groups with higher conversion rates in key metrics.
Ads Optimization
In this project, the model captured user preferences and interests to optimize ads in the application and show subscription offer screens based on the tools and content each user tends to like the most.
Credit Default Prediction
The project dealt with predicting the probability of default on each loan and determining the creditworthiness of each client. The amount and rate of the landing were decided for each loan, or if the probability of default was high, the loan request was denied.
Time Series Anomaly Detection
The model captured anomalous changes in the behavior of hourly count data crashes, analyzing the history of time series data. When the anomaly was detected, it alerted the development team to fix issues.
Statistical Guarantees for Conditional Generative Models
An applied research project was performed under the supervision of professor Arnak Dalalyan from ENSAE Paris. We introduced a convenient framework for studying conditional (adversarial) generative models from a statistical perspective. It consisted of modeling a generative device as a smooth transformation of a unit hypercube with a dimension much smaller than ambient space and measuring the quality of the generative model through integral probability metrics.
Aesthetic Predictor
A model is trained to predict whether the given photo can be considered aesthetic. The main difference between existing state-of-the-art models is that it captures company-specific standards that do not appear in open source datasets. It is also used as a content quality estimator, which helps increase the performances of other models relying on the quality score.
Education
2019 - 2021
Master's Degree in Data Science
Yerevan State University - Yerevan, Armenia
Skills
Libraries/APIs
Scikit-learn, PySpark, LSTM, PyTorch, XGBoost, Hugging Face Transformers, NumPy, Pandas, TensorFlow, Keras, Spark ML
Tools
ARIMA, Tableau, Google Analytics, Gensim, GitHub, SARIMA, Git, BigQuery, Google AI Platform, Microsoft Power BI, ChatGPT, Plotly, Azure ML Studio, Apache Airflow
Languages
SQL, Python, R, Snowflake, Falcon, Python 3
Platforms
Databricks, Amazon Web Services (AWS), Google Cloud Platform (GCP), Kubernetes, Docker, Azure, Azure SQL Data Warehouse, Dedicated SQL Pool (formerly SQL DW)
Frameworks
Spark
Paradigms
Real-time Systems
Storage
MySQL, PostgreSQL, Data Pipelines
Other
Machine Learning, Deep Learning, Data Analysis, Statistics, Data Science, Artificial Intelligence (AI), Recommendation Systems, Mathematics, Analytics, Natural Language Processing (NLP), AI Design, Neural Networks, Artificial Neural Networks (ANN), AI Programming, Forecasting, JupyterLab, Random Forests, Linear Regression, Model Development, BERT, Data Analytics, Data Reporting, Generative Pre-trained Transformers (GPT), Data Extraction, Predictive Modeling, Probability Theory, Predictive Analytics, Data Scientist, Data Modeling, Statistical Data Analysis, Large Language Models (LLMs), Transformers, Data Processing, Feature Engineering, Statistical Modeling, Data Visualization, Engineering, Torch, Reinforcement Learning, Research, Finance, Optimization, Time Series Analysis, Time Series, Google BigQuery, Architecture, Financial Modeling, Natural Language Understanding (NLU), Computer Vision, Generative Adversarial Networks (GANs), Language Models, Word Embedding, OpenAI GPT-4 API, Azure Databricks, Data-driven Marketing, Pricing Models, Algorithms, Data Manipulation, OpenAI, Prompt Engineering, Retrieval-augmented Generation (RAG), Speech-to-Text (STT), Cloud, Fine-tuning, Social Networks, Search, Dashboards, Dashboard Design, CI/CD Pipelines, Gaming, APIs, Image Generation, Google, Generative Systems, Diffusion Models, Generative Artificial Intelligence (GenAI), Text to Image, Images, Clips, Aesthetics, Content, Data Engineering, OpenAI GPT-3 API, Generative Pre-trained Transformer 3 (GPT-3), Financial Analysis, Startups, Early-stage Startups, Llama 2, PEFT, Reinforcement Learning from Human Feedback (RLHF), Medallion Architecture, Software Engineering, Customer Service Support, VoiceBot, Text-to-Speech (TTS), Machine Learning Operations (MLOps)
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