Ankit Pal is a Senior/Principal Research Engineer with a decade of experience applying NLP, deep learning, and representation learning to accelerate healthcare and clinical trials. Based in Cambridge, MA, he combines hands-on model development with practical deployments at Saama and prior roles at Prescience, focusing on graph representations, federated learning, XAI, and generative language models for healthcare data. He has contributed datasets and research adopted by major labs (Facebook AI, Google AI, Microsoft, OpenAI) and actively contributes to TensorFlow, PyTorch Geometric, and HuggingFace. His open-source project Promptify—built to improve structured outputs from LLMs and used during the Turkey–Syria earthquake relief—highlights his focus on robust prompt engineering and evaluation metrics for generative models. Ankit’s work blends rigorous research with real-world impact, from COVID cough-capture diagnostics to prompt-evaluation tooling. Outside of research he pursues boxing, jiu-jitsu, chess and contemplative observation, which he says informs his thoughtful approach to problem solving.
10 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at Harvard University
Bachelor of Technology - BTech, Computer Science, Bachelor of Technology - BTech, Computer Science at Babu Banarsi Das University, Lucknow
Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research
Role in this project:
Data Scientist
Contributions:1 release, 2 reviews, 223 commits in 3 months
Contributions summary:Ankit primarily contributed to the development of a metrics and evaluation system for generative content. They created and updated code for the `Generative_metrices.py` file, implementing functions to evaluate content generated by models like GPT-3 and ChatGPT. Additionally, they introduced prompt functions and models within the codebase, particularly focusing on Named Entity Recognition and Multi-Label classification tasks, by introducing prompt templates and util functions.
Contributions:9 pushes, 1 branch in 4 years 7 months
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.