Home

Ganesh Vengali - AI/ML Engineer

[email protected]

Location: Saint Paul, Minnesota, USA

Relocation: YES

Visa: GC EAD

Resume file: GaneshVengali_AIML_1789401604970.docx Please check the file(s) for viruses. Files are checked manually and then made available for download.

Senior AI and Machine Learning Engineer with 9+ years of experience architecting and deploying production data and ML systems across banking, healthcare, retail, and public-sector domains. Specializing over the past 3+ years in enterprise Generative AI, taking complex LLM systems from prototype into regulated production. Proven expertise in building production-grade RAG and multi-agent systems using LangChain, LangGraph, and LlamaIndex across Amazon Bedrock and Azure OpenAI. Deep technical depth in designing hybrid retrieval architectures over Pinecone, Amazon OpenSearch Service, and FAISS with advanced chunking, embeddings, and reranking. Demonstrated track record in fine-tuning open-source LLMs using PyTorch, Hugging Face Transformers, LoRA, QLoRA, and PEFT to optimize domain-specific reasoning and eliminate hallucinations. Strong background in scalable backend engineering and MLOps/LLMOps, deploying models as FastAPI microservices on Docker and Kubernetes with automated CI/CD via GitHub Actions and Azure DevOps. Comprehensive observability and evaluation experience with Langfuse, Bedrock Prompt Flows, and MLflow for groundedness scoring, drift monitoring, and prompt regression testing. Experienced operating within strictly regulated environments (HIPAA, SOX, PCI, GDPR) utilizing SHAP and LIME for model explainability and compliance. Keywords: continuous integration continuous deployment artificial intelligence machine learning