.png){kind=logo}
Ramesh Jasti
Mid-level AI/ML & MLOps Engineer specializing in cloud AI infrastructure and GenAI
Connect with Ramesh
Ramesh 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
At HPE, led and deployed an enterprise-grade LLM document intelligence platform for an insurance client, automating extraction from highly variable PDFs/scans/emails and raising field accuracy from 74% to 93%. Built a LangChain/Pinecone/OpenSearch RAG framework to cut hallucinations by 37% and operationalized LangSmith evals in CI, driving a 41% triage accuracy lift and >33% fewer incorrect resolutions while partnering closely with claims operations via HITL workflows.
Experience
Education
Key Strengths
- Led development and production deployment of an enterprise document intelligence platform for an insurance client
- Built hybrid OCR + LLM extraction pipeline improving field extraction accuracy to 93% (from 74%)
- Designed RAG grounding (LangChain + Pinecone + OpenSearch) to reduce LLM hallucinations by 37%
- Airflow orchestration of multi-stage, event-driven pipelines (S3 file drops, Kafka events) with SLA monitoring
- Implemented rigorous agent/workflow testing (golden paths, unit tests, fuzzing) and evaluation (LangSmith/TruLens)
- Established LangSmith evaluation loop in CI; improved triage accuracy by 41% and reduced incorrect resolutions by >33%
- Effective collaboration with non-technical claims operations stakeholders; built HITL dashboards and reduced correction cycles by 40%
Discover more candidates like Ramesh
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent