Venka V

About Venka V

Machine Learning Engineer with 4+ years of experience building production-grade AI systems with a focus on Generative AI, LLMs, and large-scale data platforms. Proven track record of designing low-latency, highthroughput ML systems, improving model performance, and delivering measurable business impact in financial and enterprise environments.

Experience

1. Ai Machine Learning Engineer (Generative Ai)

   JPMorganChase

   Jun 2025 — Present · US

   Architected and deployed distributed RAG system processing 2M+ financial documents, improvingcompliance accuracy by 25% and reducing manual effort by 40% Designed low-latency inference architecture (<200ms) supporting 100K+ daily requests, optimizingembedding caching and retrieval pipelines. Built scalable LLM pipelines on AWS (SageMaker, Spark) for batch + real-time inference workloads. Improved retrieval precision and reduced hallucinations by 30% via semantic search optimization andembedding tuning. Designed system trade-offs across latency, accuracy, and infrastructure cost, optimizing production LLMperformance. Implemented end-to-end MLOps platform (MLflow, Airflow, Docker, Kubernetes) enabling reproducible training and scalable deployments. Developed high-throughput document intelligence platform integrating structured + unstructured data pipelines. Collaborated with cross-functional teams to define architecture decisions, scaling strategies, and reliability improvements.

Education

• Anderson University

  Business Analytics