.png){kind=logo}
Vamsi Koppala
Mid-level Machine Learning Engineer specializing in Generative AI and RAG systems
Connect with Vamsi
Vamsi 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/ML engineer who has shipped an enterprise RAG-based Q&A system (LangChain/LlamaIndex, FAISS + Azure Cognitive Search, GPT-3.5/4 via OpenAI/Azure OpenAI) to production on Docker + Kubernetes/OpenShift, tackling hallucinations, retrieval quality, latency/cost, and RBAC/IAM security. Also partnered with operations leaders to turn manual reporting into an LLM-powered summarization and forecasting dashboard driven by real KPIs and iterative stakeholder feedback.
Experience
Education
Key Strengths
- Built and deployed an enterprise RAG Q&A platform for internal policy/document search
- Strong production LLM engineering across retrieval, generation, and scalable deployment (Docker + Kubernetes/OpenShift)
- Improved grounding and reduced hallucinations using Guardrails.ai/TruLens and structured function-calling schemas
- Optimized retrieval quality across diverse document types with chunking and hybrid search (FAISS + Azure Cognitive Search)
- Cost/latency optimization via model routing and caching
- Security-aware RAG design with role-based access and IAM-integrated retrieval filters
- Reliable evaluation approach using KPI-driven design, curated/adversarial test suites, A/B testing, and MLflow/Kubeflow metrics
- Effective cross-functional delivery: translated ops KPIs into an LLM-powered summarization/forecasting dashboard through iterative workshops
Discover more candidates like Vamsi
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent