.png){kind=logo}
Somil Shah
Mid-level AI/ML Engineer specializing in generative AI, RAG platforms, and LLM agents
Connect with Somil
Somil 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
AI/LLM engineer who has shipped 10+ production applications, including InvestIQ on GCP—a production-grade RAG due-diligence engine that ethically scrapes web/PDF sources, builds a ChromaDB knowledge base, and delivers analyst-style dashboards plus a citation-backed chat copilot. Deep focus on reliability (evidence-only answers, hard citations, refusal gating), retrieval tuning, and orchestration (Airflow/Cloud Composer), plus multi-agent systems (CrewAI with 7 specialized finance agents).
Experience
Education
Key Strengths
- Built and deployed 10+ AI/LLM production-grade applications
- End-to-end RAG system design (ingestion, vectorization, retrieval tuning, chat UX) with citations and traceability
- Strong hallucination mitigation via evidence-only answering, hard citation requirements, and refusal gating
- Orchestrated scheduled data refresh pipelines with Airflow/Cloud Composer (scrape → clean/dedupe → chunk → embed → upsert)
- Multi-agent system design and orchestration (7 specialized agents) with delegation, memory, feedback loops, and fallbacks
- Reliability engineering for AI workflows: SLOs/metrics, schema-constrained outputs, deterministic control flows, retries/fallbacks
- Testing and production observability for AI systems (unit tests, CI/CD smoke tests, logging, traces, drift alerts)
- Effective collaboration with non-technical stakeholders to translate diligence checklists into structured outputs and prompts
Discover more candidates like Somil
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent