Deployed Engineer (uk)

LangChain LangChain · Data AI · London, United Kingdom · Deployed Engineering

LangChain is seeking a Deployed Engineer in the UK to work with companies building and running AI agents in production. This role involves co-architecting and co-building agents, owning technical wins in pre-sales, helping customers deploy and operate agent-based applications, and advising on best practices. The ideal candidate has 3+ years of experience in a relevant technical role, strong Python/JavaScript skills, experience designing agent-based applications beyond simple API calls, and is comfortable working directly with customers. The role emphasizes operating AI agents in production and contributing to the platform's adoption.

What you'd actually do

  1. Co-architect and co-build production AI agents with customer engineering teams
  2. Own the technical win in pre-sales by designing POCs, answering deep technical questions, and guiding evaluations
  3. Help customers deploy and operate agent-based applications such as conversational agents, research agents, and multi-step workflows
  4. Advise customers post-sale on architecture, best practices, and roadmap-level decisions
  5. Run technical demos, trainings, and workshops for developer audiences

Skills

Required

  • 3+ years in a relevant technical role (software engineering, customer engineering, solutions engineering, founding/product engineering)
  • Python
  • JavaScript
  • systems fundamentals
  • designed agent-based or LLM-powered applications beyond simple API calls, including multi-step workflows, orchestration, and failure handling
  • working directly with customers during POCs, architecture reviews, and technical evaluations
  • explain technical tradeoffs clearly
  • build trust with developer audiences
  • Take responsibility for outcomes
  • bias toward action
  • operating AI agents in production

Nice to have

  • deployed AI agents in production, especially using LangChain, LangGraph, or similar frameworks
  • LLM evaluation
  • observability
  • guardrails
  • cloud environments (AWS, GCP, Azure)
  • containers
  • basic Kubernetes concepts
  • shipped and operated production software
  • comfortable owning systems under real-world constraints

What the JD emphasized

  • systems that real teams depend on in production
  • systems that real teams depend on in production
  • operating AI agents in production

Other signals

  • building and operating AI agents in production
  • move from prototypes to production-ready AI agents
  • deploying and operating agents at scale