Mounya Bonuga

About

ML/AI engineer with hands-on ownership of a production LLM/RAG system at Goldman Sachs, focused on workflow automation and large-scale document search for operational teams. They combine strong MLOps and backend engineering skills with practical GenAI evaluation and safety practices, and cite measurable impact including 22% better task guidance accuracy and sub-second search across millions of records.

Key Strengths

• Owned production ML/AI systems end-to-end from experimentation through deployment and monitoring
• Built scalable RAG-based workflow automation for operational document search and guidance
• Improved task guidance accuracy by 22%
• Delivered sub-second semantic search across millions of records
• Strong production ML platform skills with Docker, Kubernetes, AWS, FastAPI, GitHub Actions, and MLflow
• Applied practical LLM safety techniques including grounding checks, prompt constraints, and human-in-the-loop review
• Balanced latency, cost, and quality tradeoffs in production GenAI systems
• Iteratively improved retrieval quality through chunking, ranking, and embedding updates based on production feedback
• Designed reusable Python ML services and shared utilities that improved team velocity and reliability

Experience

Education

Skills

Languages