Senior AI Engineer

Metropolis Metropolis · Vertical AI · New York, NY +1 · Engineering Strategy & Operations

Senior AI Engineer to join Applied AI organization, focused on rebuilding company operations from an AI-first perspective. The role involves designing and shipping AI-powered tools and automation pipelines, owning systems end-to-end from prompt layer to production deployment, and partnering with Process Analysts. Key responsibilities include building AI-powered automation tools, architecting LLM-based systems (prompt pipelines, agentic workflows, RAG), building data pipelines, and owning production reliability.

What you'd actually do

  1. Design, build, and ship AI-powered automation tools and internal applications that transform manual business processes into AI-first workflows
  2. Architect and maintain LLM-based systems, including prompt pipelines, agentic workflows, tool-calling integrations, and retrieval-augmented generation (RAG) setups
  3. Build and maintain data pipelines that connect source systems (Snowflake, internal APIs, SaaS tools) to AI workflows, ensuring data quality and reliability
  4. Partner with Process Analysts to understand how business functions work today, translate requirements into engineering specifications, and iterate based on real user feedback
  5. Own production reliability for the systems you build — monitoring, alerting, and iterating on AI outputs to maintain quality over time

Skills

Required

  • 6+ years of software engineering experience
  • 2+ years of hands-on experience designing, building, and deploying LLM-based or AI-powered applications in production
  • Strong Python skills
  • building APIs, data pipelines, and backend services
  • Practical experience with LLM APIs (OpenAI, Anthropic, or similar)
  • prompt engineering
  • agentic patterns (function calling, multi-step reasoning, tool use)
  • data engineering fundamentals: SQL, data transformation, working with cloud data warehouses (Snowflake preferred)
  • workflow orchestration tools (e.g., Airflow, Prefect, or similar)
  • cloud infrastructure (AWS preferred)
  • strong instinct for product quality
  • Ability to work autonomously in a fast-moving environment
  • manage competing priorities
  • ship iteratively

Nice to have

  • Experience with vector databases, embeddings, or semantic search

What the JD emphasized

  • AI-powered automation tools and internal applications
  • LLM-based systems
  • agentic workflows
  • tool-calling integrations
  • retrieval-augmented generation (RAG) setups
  • production deployment
  • production reliability

Other signals

  • building and shipping AI-powered tools
  • LLM-based systems
  • production deployment
  • AI-first perspective