.png){kind=logo}
Snehitha Penumaka
Mid-level AI/ML Engineer specializing in predictive modeling and cloud ML pipelines
Connect with Snehitha
Snehitha 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
LLM engineer/data engineer who has deployed production RAG systems for internal-document Q&A, building end-to-end ingestion, embedding, vector search, and FastAPI serving while actively reducing hallucinations and latency through rigorous retrieval tuning and caching. Also experienced in orchestrating cloud data pipelines (Airflow, AWS Glue, Azure Data Factory) and partnering with non-technical business teams to deliver AI solutions like automated document review.
Experience
Education
Key Strengths
- Built and deployed a production LLM/RAG Q&A system grounded in internal documents
- Systematic retrieval tuning via chunk-size/overlap experiments and embedding model A/B tests
- Reduced hallucinations using context-only guardrails and improved retrieval relevance (top-k/threshold tuning)
- Designed low-latency architecture with caching and API-based serving (FastAPI)
- Strong orchestration experience (Airflow/Glue/Data Factory) including DAG dependencies, retries, and failure recovery
- Debugged intermittent Airflow failures by implementing a custom S3 file-readiness sensor
- Reliability-focused evaluation approach: unit/scenario/edge-case tests, offline eval sets, and post-deploy KPI monitoring
- Effective collaboration with non-technical stakeholders; translated business needs into an LLM prototype and iterated to deployment
Discover more candidates like Snehitha
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent