Dinesh Kumar Patibandla

About

ML Engineer with recent Goldman Sachs experience building and deploying a production RAG/LLM assistant for summarization, drafting, and internal knowledge retrieval across financial, risk, and compliance documents. Designed for heavy regulatory constraints and scaled to 10,000+ concurrent users using Kubernetes-based orchestration, dynamic LLM routing, and rigorous testing (adversarial prompts, A/B tests, load simulations) with privacy controls like differential privacy.

Experience

Education

Key Strengths

• Built and deployed production LLM assistant for document summarization, drafting, and internal knowledge retrieval in a regulated financial environment
• Scaled LLM/RAG platform to support 10,000+ concurrent users with autoscaling Kubernetes architecture
• Performance engineering for LLM systems (load testing, async processing, caching, vector search optimizations) to reduce peak latency
• Strong compliance and privacy focus (encryption, privacy controls, differential privacy) to meet financial/regulatory requirements
• Systematic evaluation methodology (benchmark datasets, adversarial testing, A/B tests, high-load simulations) for reliability and safety
• Effective cross-functional collaboration with compliance and risk stakeholders to translate requirements into guardrails and controls