Strong proficiency in Python, with hands-on experience building production-grade software (not just notebooks/prototypes). Practical experience with agentic frameworks such as LangChain, LangGraph, or similar. Solid understanding of LLM fundamentals — prompting, tool/function calling, RAG, embeddings, context management, memory systems. Experience designing modular, platform-agnostic architectures (i.e., not tightly coupled to a single LLM vendor or cloud provider). Understanding of SDLC processes (CI/CD, version control, code review, testing) and how AI agents can augment or automate them. Experience with API design, microservices, and building extensible/reusable frameworks or SDKs. Familiarity with agent evaluation and observability tooling (e.g., LangSmith, tracing frameworks, custom eval harnesses). Strong grasp of governance concepts for AI systems — guardrails, access control, auditability, human oversight.