3+ years of hands-on experience with machine learning models, particularly large language models (LLMs). Practical experience building and optimizing Retrieval-Augmented Generation (RAG) systems. Proven experience training, fine-tuning, or adapting models for specific domains or use cases. Experience designing and implementing AI evaluation methodologies and metrics. Proficiency in Go and Python. Experience with LangChain/LangGraph or similar AI orchestration frameworks. Demonstrated ability to prototype quickly and iterate based on user feedback. Experience with containerization technologies (Docker, Kubernetes) or developer tooling (preferred). Knowledge of vector databases and semantic search technologies (preferred). Experience with AI safety, hallucination detection, and reliability techniques (preferred).