.png){kind=logo}
Eranda Sooriyarachchi
Mid-level AI Engineer specializing in RAG, conversational AI, and agentic systems
Connect with Eranda
Eranda 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 deployed a production RAG-based clinical decision support assistant at MedLib, focused on fast, trustworthy answers from large medical documents. Demonstrates deep practical experience improving retrieval accuracy (semantic chunking + metadata-aware search), controlling hallucinations with grounded generation and thresholds, and adding clinician-requested citations using chunk metadata, with evaluation driven by healthcare professional review.
Experience
Education
Key Strengths
- Built and deployed a production LLM-powered clinical decision support assistant
- Designed end-to-end RAG pipeline (ingestion → embeddings/vector DB → retrieval → grounded generation with citations)
- Improved retrieval quality via semantic chunking and metadata-aware filtering/re-ranking
- Reduced hallucination risk by constraining answers to retrieved context and using retrieval thresholds
- Optimized latency and cost with caching
- Strong evaluation discipline: stage-level + system-level metrics with clinician gold-standard review
- Modular LLM workflow design using LangChain; able to swap models/retrieval strategies without rewriting pipeline
- Implemented reliability practices: schema validation, guardrails, logging/trace inspection, fallback behavior, production monitoring
- Effective collaboration with non-technical clinical stakeholders; ran workshops/feedback sessions that drove product changes (citations)
Discover more candidates like Eranda
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent