No cost, no commitment - we'll make a personal intro
SS
Saptarshi Sengupta
Mid-level NLP/LLM Researcher specializing in question answering and retrieval-augmented generation
BoschPenn State UniversityState College, PA6 Years ExperienceMid LevelWorks On-Site
Connect with Saptarshi
Saptarshi already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Typically responds within 24 hours
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.
Hire with Reval
Find your next great hire
Our AI agents source, screen, and vet candidates for your open roles. Get qualified candidates within 48 hours.
Natural Language Processing (NLP)Large Language Models (LLMs)Question Answering (QA)Medical/Healthcare NLPLow-resource NLPMultimodal Question AnsweringRetrieval and Tool Retrieval for LLM AgentsSynthetic Data GenerationKnowledge Graph EmbeddingsSemantic Evaluation (SemEval)Word Sense Disambiguation and Induction
Mid-level investor specializing in cross-border private equity and tech
Cambridge, MA4y exp
Mossavar-Rahmani CenterHarvard University
“Investor/banker with cross-border sourcing experience spanning JPMorgan, Ascendant, Pumavira, and EQD, covering AI, advanced manufacturing, TMT, and consumer healthcare. Stands out for turning cold founder outreach into long-term banking engagements and for combining high-volume sourcing with rigorous early-stage commercial and regulatory screening.”
Intern Machine Learning Engineer specializing in LLM agents and multimodal reasoning
Mountain View, CA2y exp
Corvic AICarnegie Mellon University
“LLM/agent engineer who built a production code-generation agent at Corvic AI that lets non-technical users query CSV/tabular data in natural language by generating and executing Python. Focused on making LLM systems reliable and scalable via schema-aware validation, sandboxed execution-feedback retries, prompt caching/embeddings, async execution, and high-throughput data processing with Polars; also partnered with Adobe product/marketing to ship brand-aligned AI content generation for email and push notifications.”
Executive AI founder specializing in machine learning for drug discovery
San Diego, CA15y exp
KekulaiHarvard University
“Entrepreneur building an AI-driven small molecule biotech startup who has already raised $5M from major venture capital investors. Brings 3 years of fundraising experience and a thoughtful approach to aligning investors with different risk profiles across financing stages, paired with strong conviction around founding high-risk, high-upside companies.”