.png){kind=logo}
SS
Saptarshi Sengupta
Mid-level NLP/LLM Researcher specializing in question answering and retrieval-augmented generation
State College, PANLP and Large Language Model Intern6 years experienceMid-LevelArtificial IntelligenceTechnologySaaS
ScreenedIdentity Verified
Connect with Saptarshi
Saptarshi already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Built ToolDreamer, a framework for selecting relevant tools for LLM agents by training a retriever on LLM-generated reasoning traces, and has hands-on experience building multi-agent systems in AutoGen (MAG-V) focused on question generation and tool-trajectory verification. Currently works as an AI-guides supervisor at Penn State, regularly communicating AI concepts to non-technical stakeholders.
Experience
NLP and Large Language Model InternRobert Bosch LLC
Machine Learning Applied Scientist InternSplunk
Graduate Research AssistantThe Pennsylvania State University
Graduate Teaching AssistantThe Pennsylvania State University
Graduate Teaching AssistantUniversity of Minnesota Duluth
Graduate Research AssistantUniversity of Minnesota Duluth
Research InternJadavpur University
Education
The Pennsylvania State Universitydoctorate, Informatics
University of Minnesota Duluthmaster, Computer Science (2020)
St. Thomas’ College of Engineering and Technology (STCET)bachelor, Computer Science & Engineering (2017)
Key Strengths
- Designed and led development of a multi-agent framework (MAG-V) in AutoGen
- Strong retrieval-first approach (BM25 baseline → dense/LLM retrievers) with pragmatic model selection
- End-to-end evaluation mindset: bootstrapping datasets, synthetic augmentation, metric-based + qualitative analysis
- Performance/latency awareness and inference optimization using multi-GPU and reduced precision
Discover more candidates like Saptarshi
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent