.png){kind=logo}
SD
Sanjana Duvva
Mid-level AI/ML Engineer specializing in Generative AI, LLMOps, and MLOps
AI/ML Engineer5 years experienceMid-LevelFinancial ServicesBankingHealthcare
ScreenedIdentity Verified
Connect with Sanjana
Sanjana 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 an AWS-based LLM/RAG ticket triage and knowledge retrieval system (Pinecone/FAISS + Step Functions + MLflow) that cut support resolution time by 20%. Demonstrates strong production focus on hallucination reduction, PII security, and low-latency orchestration, with measurable evaluation improvements (e.g., ~25% grounding accuracy gain via re-ranking) and proven collaboration with support operations stakeholders.
Experience
AI/ML EngineerWells Fargo
AI/ML EngineerUnitedHealth Group
Software EngineerTarget Corporation
Education
University of North Texasmaster, Computer Science
Andhra Universitybachelor, Computer Science
Key Strengths
- Built and deployed production LLM-powered ticket triage + knowledge retrieval system on AWS
- Reduced support ticket resolution time by 20%
- Hallucination mitigation via strict RAG constraints, cross-encoder re-ranking, answer validation, and prompt guardrails
- Designed reliable multi-step RAG orchestration with Step Functions (parallel branches, custom retries, rollback paths)
- Evaluation-driven iteration: improved grounding accuracy ~25% by changing retrieval strategy and adding re-ranking
- Strong approach to agent/workflow reliability: modular design, unit + scenario testing, A/B testing, metric-driven monitoring (accuracy, grounding, latency, human override rate)
- Effective collaboration with non-technical stakeholders to translate operational pain points into requirements (labels, thresholds, fallback behaviors)
Discover more candidates like Sanjana
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent