Anindyadeep Sannigrahi
Founder at LiteFold
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolAnindyadeep Sannigrahi is a founder and ML engineer with six years of hands-on experience building LLM systems, graph ML, and computer vision solutions from research prototypes to production SDKs. Based in Bengaluru, he led open-source engineering at Prem—shipping widely used artifacts like Prem-1B-SQL (30K+ HF downloads) and maintaining Prem’s SDK integrations across projects such as DSPy and LangChain. He contributed core metric implementations and test automation for LLM evaluation frameworks and integrated Prem AI into Stanford’s DSPy, reflecting a strong backend and evaluation focus. Earlier research produced a state-of-the-art link prediction architecture (MVGAE) and practical ML systems for video/image pipelines and protein folding, the latter seeding his current venture LiteFold focused on AI co-scientists for therapeutics. Equally comfortable publishing technical blogs and running benchmarks, he combines production-grade engineering with research-driven curiosity and active open-source stewardship.
6 years of coding experience
3 years of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at KIIT - Kalinga Institute of Industrial Technology
Github Skills (13)
apim10
rouge10
nlp10
bleu10
api10
python10
evaluation10
natural-language-processing10
metric10
testing10
back-end-development9
machine-learning9
unit-testing9
Programming languages (12)
Github contributions (5)
stanfordnlp/dspy
Mar 2024 - Oct 2024
DSPy: The framework for programming—not prompting—language models
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:25 reviews, 8 PRs, 61 comments in 7 months
Contributions summary:Anindyadeep primarily contributed to integrating the Prem AI SDK into the dspy framework. They implemented a `PremAI` module to interact with the Prem AI API, enabling the use of Prem AI models within dspy. Their work included setting up the necessary configurations, handling API requests, and integrating the new module into the existing dspy structure, which involved changes in `__init__.py` files.
nlpbertknowledgepredictlanguage-models
confident-ai/deepeval
Oct 2023 - Dec 2024
The LLM Evaluation Framework
Role in this project:Back-end Developer & Test Automation Engineer
Back-end Developer & Test Automation EngineerContributions:3 reviews, 15 PRs, 34 comments in 1 year 2 months
Contributions summary:Anindyadeep primarily contributed to the development of the LLM evaluation framework by adding core metric calculation classes and utility functions. Their work includes implementing statistical and model-based metrics using libraries such as Rouge, BLEU, and BERTScore. The user also refactored and organized the codebase, including relocating metrics and renaming files, and added tests for the exact match and other scoring methods to ensure the framework's functionality. The contributions reflect an emphasis on both core functionality and ensuring code quality through testing.
evaluation-frameworkevaluation-metricsllm-evaluationllm-evaluation-frameworkllm-evaluation-metrics
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.