.png){kind=logo}
Vedant Jagtap
Junior AI/NLP Engineer specializing in LLM systems and RAG
Connect with Vedant
Vedant 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
LLM/agent engineer who shipped a two-stage AI recruitment screening platform at Foursquare that automated resume ingestion through behavioral assessment, delivering an 85% reduction in screening time across 5,000+ applications with auditability and confidence-gated decisions. Also built a multi-agent benchmarking framework using MCP tool interfaces and a RAGAS + LangSmith evaluation/observability stack, including async re-architecture that cut production latency by 50%.
Experience
Education
Key Strengths
- Shipped LLM-powered recruitment screening platform automating end-to-end pre-interview workflow
- Achieved 85% reduction in screening time across 5,000+ applications
- Designed production reliability controls for non-deterministic LLM outputs (validation layer, deterministic scoring, confidence gating)
- Built auditable decisioning with SQL-based audit trail for every rejection/advancement
- Strong agent orchestration design (multi-agent handoffs, state management, iteration limits to prevent runaway loops)
- Implemented robust evaluation and monitoring (RAGAS offline benchmarks, LangSmith online tracing, regression suite)
- Data-driven performance optimization using tracing; re-architected to async parallelization cutting latency by 50%
- Handled messy/ERP-like knowledge bases with preprocessing, recency-weighted retrieval, and multi-tenant permissioned namespaces
- Designed safe fallbacks (similarity thresholds, JSON validation errors, safe default to human escalation)
Discover more candidates like Vedant
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent