Saikat Chakraborty
Research Scientist at Micosoft Research
Redmond, Washington, United States
Summary
🤩
RockstarSaikat Chakraborty is a Senior Researcher at Microsoft Research and Associate Editor for ACM Transactions on Software Engineering and Methodology, with 11 years of experience building and evaluating large language models for code. He specializes in turning execution, testing, program analysis, and formal verification into structured training and evaluation signals that make code LLMs reliable in production. His projects—DeepTest, DeepProof, and the open-source FStarDataset—bridge agentic testing, theorem proving, and verified-program benchmarks, and have driven state-of-the-art results on F* and Coq/Lean suites. Saikat’s work uniquely integrates real-time verification and reinforcement learning to move correctness from an offline metric into direct supervision. Trained as a PhD computer scientist from Columbia with internships at Google and Meta, he combines rigorous formal methods with production-focused engineering to advance trustworthy AI for software engineering.
11 years of coding experience
Stackoverflow
11reputation
650reached
1answer
0questions
Github Skills (34)
representation-learning10
network-programming10
quic10
z310
examine10
rust10
cpp10
csharp10
cross-platform9
language-model9
textual9
code-intelligence9
programming-language7
natural-language-processing7
nlp7
Programming languages (9)
Github contributions (5)
saikat107/GumTreeTest
Nov 2017 - Jul 2022
Contributions:33 pushes, 3 branches in 4 years 9 months
saikat107/OpenNMT-py
Aug 2018 - Jul 2020
Open Source Neural Machine Translation in PyTorch
Contributions:83 pushes, 6 branches in 1 year 11 months
pytorchmachine-translationtranslationdeep-learningtorch
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.