Robust experience designing and governing multi-agent AI architecture.
Hands-on experience with Vertex AI and GCP AI services.
Strong prompt engineering experience with LLMs such as GPT, Claude, and Gemini.
Experience with LangChain, Semantic Kernel, and AI agent frameworks.
Experience designing RAG pipelines using secure coding knowledge packs.
Robust knowledge of vector databases and embeddings, including Pinecone, FAISS, and Vertex embeddings.
Strong Python experience and experience with ML pipelines.
Experience designing agent memory using vector databases or knowledge graphs.
Experience with LLM evaluation frameworks, including accuracy, false positives, latency, and judge scoring models.
Ability to design secure, explainable AI outputs and governance for model versioning and evaluation.