Samar Srivastava is a pragmatic Data Scientist II with 9 years of experience building production-grade NLP and LLM systems for recruitment tech, currently leading end-to-end design and deployment of multi-agent LLM + RAG pipelines at WiseStep. He has a track record of turning research into reliable services—shipping a CV parser processing 1M+ resumes/week, a candidate deduplication engine, and a FAISS-backed retrieval layer that cut outreach time 6x. Samar blends model work, prompt orchestration and inference optimizations with engineering best practices like Dockerized microservices, Airflow orchestration, Kafka streaming, and observability on AWS. He favors lightweight embedding and retrieval tradeoffs to achieve near-real-time responses at scale and has reduced manual tagging and sync latencies across platforms. Based in Gurugram, he pairs deep NLP craft (Spacy, NLTK) with hands-on system design to prioritize reliability, cost, and latency in production AI.
9 years of coding experience
4 years of employment as a software developer
Full Stack Web Development Certification, Computer Software Engineering, Full Stack Web Development Certification, Computer Software Engineering at freeCodeCamp
Bachelor of Technology - BTech, Computer Science, Bachelor of Technology - BTech, Computer Science at Hindustan College of science and technology
High School, High School Equivalence Certificate Program, High School, High School Equivalence Certificate Program at St. Francis Convent School
A simple Python script to scrap Airbnb data for a given location, dates and number of guests.
Contributions:1 PR, 8 pushes, 1 branch in 2 years 6 months
pythonairbnbguestspython-scriptscrap
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.