Manish Shetty
Graduate Student Researcher
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolManish Shetty is a PhD student at UC Berkeley and an ML researcher with eight years of experience focused at the intersection of programming languages and ML systems, actively working on AI4Code. He has research internships at Google DeepMind and Microsoft and was a research fellow at Microsoft Research, bridging academic rigor with industry-scale problems. Manish contributes to open-source tooling for "programming—not prompting" language models—most notably adding Assert and Suggest primitives and bootstrapping improvements to DSPy to make LM programs more debuggable and self-correcting. He leads and contributes to projects such as GSO, Syzygy, R2E, RepoChat/Chatbot-Arena and AIOpsLab, applying ML systems ideas to developer productivity. Based in Bengaluru, he pairs a strong engineering background from PES University with PhD-level research to push practical, verifiable ML tooling.
8 years of coding experience
1 year of employment as a software developer
Bachelor of Technology - BTech, Computer Science, First Class with Honors (CGPA 9.51), Bachelor of Technology - BTech, Computer Science, First Class with Honors (CGPA 9.51) at PES UniversityDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at UC Berkeley Electrical Engineering & Computer Sciences (EECS)
Tamil, Kannada, Hindi, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (8)
error-handling10
machine-learning10
backtracking10
dnspy10
python10
computer-engineering9
nlp9
git7
Programming languages (6)
Github contributions (5)
stanfordnlp/dspy
Sep 2023 - Jan 2024
DSPy: The framework for programming—not prompting—language models
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 6 PRs, 19 pushes in 4 months
Contributions summary:Manish contributed to the `dspy` repository by adding and modifying assertion support within the context of a question-answering framework. Their work involved introducing and refining mechanisms for error handling and backtracking, specifically through the implementation of `Assert` and `Suggest` primitives. These changes aimed to improve the robustness and reliability of DSPy programs, allowing for more effective debugging and self-correction within the language model workflows. Furthermore, they focused on analyzing validation failures and optimizing the bootstrapping process.
nlpbertknowledgepredictlanguage-models
manishshettym/tart
May 2023 - Jul 2024
tart: tensor abstracted relations and topologies
Contributions:5 releases, 33 PRs, 40 pushes in 1 year 1 month
graphsrelationstensors
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.