Looking for a job

Satarupa Deb

@satarupadeb

Message

I build open-source AI, RAG, machine translation, and cloud-native security systems.

India

Message

What I'm looking for

I'm looking to build impactful AI, machine learning, RAG, translation, and cloud-native security systems, while contributing to open-source projects and applied research.

I'm contributing Go security tooling and production RAG systems at OpenSSF, including OSPS Baseline checks, Privateer improvements, and fine-tuned Qwen2.5 models for schema generation and grounded Q&A. I also co-authored CNCF's IAM Whitepaper and research secure authentication and authorization patterns for cloud-native systems.

I've built Bengali-to-English speech translation models, medical RAG pipelines, and AI research tools, with work accepted at MT Summit 2025 and WMT 2026. Earlier, I optimized plasma calculations at Bhabha Atomic Research Centre and built NLP systems for sentiment analysis and translation.

Experience

Work history, roles, and key accomplishments

Current

Academic Consultant

Current

Emeritus

Nov 2024 - Present (1 year 11 months)

Evaluated learner business proposals across 400+ course runs for programs associated with MIT, NUS, and IITs, applying expertise in business strategy, AI/ML, data science, and research. Recognized with the Best Performer Award for FY2026.

Business Strategy AI ML Data Science Research Learner Assessment Feedback

Current

Software Developer

Current

OpenSSF

Sep 2024 - Present (2 years 1 month)

Contributed Go CLI improvements and code review fixes to Privateer and Privateer SDK, including scoped error-handling corrections for config loading and Gemara Layer 3 migration work. Implemented OSPS Baseline security control checks in pvtr-github-repo-scanner and fine-tuned Qwen2.5-3B models for schema generation and grounded QA.

Go CLI Development Code Review Security Controls Qwen2.5 Ollama RAG Unit Testing

Current

Research Project Member

Current

Cloud Native Computing Foundation

Sep 2024 - Present (2 years 1 month)

Collaborated as a project member and co-author of the Identity and Access Management Whitepaper, contributing to best practices for the cloud-native ecosystem. Currently working on the MCP Authentication and Authorization Whitepaper initiative under CNAI.

IAM OAuth Zero Trust Workload Identity Policy Based Access Control UML Research

ML Research Intern

SpeechT

Dec 2024 - Apr 2025 (4 months)

Built an open-source ASR Model and MT Model based on whisper-small and NLLB-600 for Bengali-to-English translation tasks. Conducted research and compiled findings into a paper accepted to the 20th MT Summit 2025.

ASR Machine Translation Whisper NLLB 200 Research Paper Writing

Software Engineering Intern

Bhabha Atomic Research Centre

Feb 2024 - Apr 2024 (2 months)

Optimized plasma density calculation program, reducing runtime by 25%, analyzing Argon plasma behavior across a 5000 K - 40000 K temperature range. Designed and implemented the Saha ionization equation solver for oxygen plasma, reducing calculation time by 12%.

Python Fortran Plasma Physics Optimization Saha Ionization Equation

Machine Learning Intern

Open Science Labs

Jan 2024 - Apr 2024 (3 months)

Engineered a RAG pipeline using the Llama-2-7B model and FHIR data to automate medical conversation summaries, processing 30 conversations/minute. Built API integrations between LLM and FHIR endpoints, reducing data retrieval latency by 50%.

Python PyTorch RAG LLM LLaMA 2 FHIR API Integration

Machine Learning Intern

KaggleX Mentorship

Dec 2022 - Mar 2023 (3 months)

Scraped 10K+ crypto tweets using Twitter API v1.1, achieving 90% data quality with a preprocessing pipeline. Fine-tuned RoBERTa model to achieve 82% sentiment classification accuracy on crypto market tweets and created a visualization dashboard.

Python Hugging Face NLP Twitter API RoBERTa Sentiment Analysis Data Visualization

Education

Degrees, certifications, and relevant coursework

Birla Institute of Technology, Mesra

Bachelor of Technology, Computer Science and Engineering

Grade: 8.7 CGPA

Activities and societies: Relevant coursework: Data structures, Algorithms, Software engineering, Linear Algebra, Machine Learning, Data Mining. Accomplishments: AIR 3864 (GATE DA'24), Google Girl Hackathon India 2023 (Top 2.5%) & Covid-19 Gameathon 2021 (First Runner-up).

Bachelor of Technology in Computer Science and Engineering with a concentration in Artificial Intelligence/Machine Learning, completed in November 2024 with a CGPA of 8.7 and First Class with Distinction.