.png){kind=logo}
Sahithi M
Mid-level GenAI/ML Engineer specializing in LLM applications and enterprise automation
Connect with Sahithi
Sahithi 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 shipped a production LLM-powered healthcare support agent at UnitedHealthGroup, using LangChain + FAISS RAG on AWS SageMaker with CloudWatch monitoring and human-in-the-loop fallbacks for safety. Strong focus on reliability engineering (confidence gating, retries/timeouts, caching) and continuous evaluation loops; reported ~40% improvement in query resolution efficiency while reducing manual support workload.
Find your next great hire
Our AI agents source, screen, and vet candidates for your open roles. Get qualified candidates within 48 hours.
Key Strengths
- Shipped production LLM healthcare agent automating benefits and care navigation queries
- Improved query resolution efficiency by ~40%
- Designed safety-first reliability with low-confidence fallback routing to human agents
- End-to-end RAG architecture with tool/API integration and JSON-structured outputs
- Built robust orchestration with validation checkpoints to prevent error propagation
- Handled real-world latency/failures using async calls, timeouts, retries with exponential backoff, and caching
- Established offline + online evaluation/monitoring loops (latency, fallback rate, satisfaction signals) and iterated based on log-driven error analysis
- Improved retrieval precision by refining embeddings, chunking, metadata, and similarity thresholds to reduce fallback rates
- Integrated with messy EMR/policy data using schema validation, transformation rules, RBAC permission checks, and idempotent actions
Like what you see? We'll introduce you to Sahithi directly.
Experience
Education
Skills
Languages
Certifications
Browse Similar
Similar Candidates
Senior Machine Learning & GenAI Engineer specializing in LLM systems and data pipelines
Mid-level Agentic AI & ML Engineer specializing in LLM agents and RAG systems
YAKKALI PAVAN
Mid-level Machine Learning & Generative AI Engineer specializing in NLP, CV, and RAG systems
“Built and deployed a production LLM-powered RAG document intelligence system used by non-technical enterprise stakeholders, cutting document search time by 40%+ while improving answer consistency. Demonstrates strong MLOps/data workflow orchestration (Airflow, AWS Step Functions, managed schedulers across GCP/Azure) and a metrics-driven approach to reliability, evaluation, and cost/latency optimization with guardrails and observability.”
Sri Charan Reddy Mallu
Mid-Level Software Development Engineer specializing in GenAI and full-stack cloud systems
“Full-stack engineer with experience across Magna, C3.ai, and Amazon, building GenAI-enabled products and finance transaction systems. Has shipped Next.js (App Router) + TypeScript features backed by Go/Python RAG pipelines, and emphasizes production quality via load testing, Selenium regression coverage, LLM-aware integration testing, and Azure observability. Also built LangGraph-orchestrated multi-step content generation workflows with robust retry/idempotency strategies.”
Senior Data/GenAI Engineer specializing in cloud-native ML, RAG, and real-time data platforms
Mid-level Generative AI Engineer specializing in LLM automation, RAG, and NLP microservices
Interested in Sahithi?
We'll personally introduce you - no strings attached.
Build your dream team with Reval
Our AI agents source, screen, and vet candidates for your open roles. Get qualified, high-intent candidates on your desk within 48 hours.
Discover more candidates like Sahithi
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent