
Meghana Bhange
Software Developer
Meghana is a machine learning engineer with a passion for solving problems in a data-driven manner. She has experience in natural language processing and has previously published at a conference and given talks on custom entity detection at the PyData meetup in Bangalore. Meghana is passionate about working on creative projects and always looks for new ways to apply her skills.
Portfolio
Experience
Machine Learning - 2 yearsKubernetes - 2 yearsPython - 2 yearsNatural Language Processing (NLP) - 2 yearsGPT - 2 yearsAmazon SageMaker - 1 yearData Engineering - 1 yearDjango - 1 yearAvailability
Preferred Environment
Visual Studio Code (VS Code), Slack, Python, Generative Pre-trained Transformers (GPT), GPT, Natural Language Processing (NLP)
The most amazing...
...project I've worked on is developing an end-to-end custom recognition service on resource-constrained code-mixed settings with low latency requirements.
Work Experience
Affiliated Researcher
TISL Lab at ETS Montreal
- Researched model extraction attacks on machine learning systems with counterfactual explanation APIs.
- Modeled an adversary that can leverage the information provided by counterfactual explanations to build high-fidelity and high-accuracy model extraction attacks.
- Benchmarked the model performance on the Folktables dataset, with the extracted model gaining fidelity of around 97.6%.
OpenAI Developer
Zurney.app (via Toptal)
- Built a FastAPI back end with GPT-3 API integration to generate a travel itinerary for a trip and extract locations. These locations were then geo-encoded with co-ordinates.
- Built a Next.js app to display the travel itinerary and show the geo-locations on Google Maps color-codes corresponding to days in the trip and information about each location.
- Dockerized and deployed both the FastAPI back end and Next.js front end to DigitalOcean.
Machine Learning Engineer
Hunters.ai
- Researched and built analytical tools for evaluating threat-hunting detectors and understanding abnormal patterns in detection outputs.
- Organized the monitoring and quality check infrastructure in machine learning detectors.
- Created a framework for deep investigation of threats.
Machine Learning Engineer
The Verloop.io
- Contributed to the intent recognition service using a sentence transformer to improve the top-K recall and accuracy, which improved F1 by 40% absolute.
- Designed, built, and deployed a multi-lingual name recognition service across all clients.
- Evaluated the performance of various language models like ULMFiT and VAMPIRE for low-resource language contexts.
- Created synthetic training data for FAQ systems in a chatbot using Generative Pre-trained Transformer 3 (GPT3) AI.
Machine Learning Intern
The Verloop.io
- Created a person-name extractor customized for multilingual conversations. Tweaked Flair, Facebook's natural language processing library, to work on low-latency use cases in English, Spanish, and French.
- Improved the final model achieves by 47% in F1 compared to the previously deployed FastText mode.
- Deployed the developed multilingual name extractor to production with overall latency of under 500 milliseconds.
Experience
Model Extraction Attack Using Counterfactual Explanation
LitNER | Literature Named Entity Recognition
https://github.com/meghanabhange/litNERHinglish Twitter Sentiment Detection | SemEval2020
https://arxiv.org/abs/2008.09820Wikipedia Textbook Assistant
https://github.com/meghanabhange/Wikipedia-Textbook-AssistantArtificial Insanity (Cards Against Humanity with Stable Diffusion) | Toptal Hackathon
I benchmarked performance in terms of quality and latency for DALLE and Stable Diffusion. Also, I deployed the final model on FastAPI to make it easier to integrate with the rest of the back end. The solution won the second prize in the Hackathon.
Skills
Languages
Python, SQL, Python 3
Other
Machine Learning, Natural Language Processing (NLP), Artificial Intelligence (AI), Deep Learning, APIs, Text Generation, Language Models, GPT, Data Engineering, Chatbots, OpenAI, AI Design, Machine Learning Operations (MLOps), Large Language Model (LLM), Computational Linguistics, Generative Pre-trained Transformers (GPT), Research, Streamlit, Transfer Learning, BERT, Signals, Information Theory, Custom BERT, Stable Diffusion, DALL-E, FastAPI, Inference API, Speech Recognition, Web Development, DaVinci, Systems, ChatGPT
Frameworks
Django, Flask, Next.js
Libraries/APIs
Pandas, Scikit-learn, SpaCy
Storage
Data Pipelines, PostgreSQL, Google Cloud
Tools
Slack, Named-entity Recognition (NER), Amazon SageMaker
Platforms
Kubernetes, Google Cloud Platform (GCP), Amazon Web Services (AWS), Visual Studio Code (VS Code), DigitalOcean
Industry Expertise
Cybersecurity
Education
Bachelor's Degree in Electronics and Telecommunication Engineering
Savitribai Phule Pune University - Pune, India