.png){kind=logo}
Shravan Ramamoorthy
Mid-level Full-Stack Engineer specializing in enterprise AI systems
Connect with Shravan
Shravan 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 and productionized an AI NL-to-SQL capability inside legacy accounts receivable software (React + Spring Boot + Postgres/pgvector RAG), adding semantic caching and a SELECT-only validation layer to satisfy infosec. Achieved measurable impact (3 days to seconds turnaround, 60% token cost reduction, 50% latency reduction) with strong adoption (40 analysts, 50+ queries/week) and documented/monitored via Confluence + logging and user feedback loops.
Experience
Education
Key Strengths
- Owned end-to-end production delivery (frontend, backend, data, infra) of NL-to-SQL feature
- Delivered major business impact: data request turnaround reduced from ~3 days to seconds
- Cost/latency optimization: reduced token costs by 60% and latency by 50% via RAG + semantic cache
- Strong AI guardrails for infosec: SELECT-only SQL validation blocking injections/malformed queries
- Prompt design depth: structured system prompt with 50+ domain-expert-validated examples for messy legacy schema
- Production adoption signal: 40 analysts using system with 50+ queries/week
- Legacy modernization via additive architecture (layered AI on top of legacy system) with milestone query-suite validation
- High-autonomy stakeholder management across 3 groups with conflicting requirements; unblocked production by addressing infosec needs
- Product/UX tradeoff leadership with CTO: simplified drag-and-drop event builder via constrained components/layouts
Discover more candidates like Shravan
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent