Experience with AWS Bedrock or other managed foundation-model platforms
Hands-on experience with MCP (Model Context Protocol) or similar approaches for connecting AI to enterprise tools and data
LLM evaluation, observability, monitoring, or AI quality experience
Experience with LangChain, LangGraph, or similar frameworks
Vector database or search technology experience
Experience implementing AI security, governance, or responsible AI practices
Experience building internal developer platforms, SDKs, APIs, or reusable infrastructure for engineering teams
5+ years in data engineering, platform engineering, backend engineering, or a related discipline, with experience building and operating production systems
Strong Python and SQL
Hands-on experience building and deploying production applications or services using LLMs / generative AI
Experience with RAG, embeddings, vector search, tool/function calling, AI agents, or enterprise knowledge systems
Strong data engineering fundamentals, including pipelines, data modeling, data quality, and secure data access
Experience with Snowflake, Databricks, or comparable modern data platforms, plus tools such as dbt, Airflow, or similar
Experience building shared AI infrastructure, platforms, or reusable AI capabilities, rather than only integrating AI into individual applications
Experience taking AI systems from experimentation to reliable production
Solid understanding of security, authentication/authorization, privacy, and data governance
Strong communicator who can translate ambiguous AI opportunities into practical engineering solutions across teams