Lead Data Scientist · Thoughtworks Singapore

Ravi Vats

I am a Lead Data Scientist at Thoughtworks Singapore, where I build LLM agent systems and RAG applications for public sector companies. Previously at Grab, I shipped ML and LLM systems at production scale, fine-tuning Llama 3.1 with LoRA for multilingual content generation across ten Southeast Asian languages, building few-shot RAG pipelines with FAISS for continuous knowledge updates post-fine-tuning, and designing agentic translation workflows with LangGraph that served more than one million users daily. My work at Grab also spanned distributed systems, anomaly detection on infrastructure spend, and high-throughput microservices handling over five million orders per day. I hold an M.S. in Computer Science (Machine Learning) from Georgia Tech, where I also worked as a Research Assistant on combining GNNs with reinforcement learning. This talk draws directly from my experience evolving RAG evaluation strategies as retrieval complexity grew in production.