Deployed Architect, Professional Services (London)

LangChain is a leading AI agent engineering platform, having raised $125 million in Series B funding from top-tier investors including Sequoia, Benchmark, and IVP. The company provides comprehensive tooling for building, evaluating, deploying, and operating intelligent agents at scale, serving over 6,000 active customers including five of the Fortune 10 and 35% of the Fortune 500. With 100 million monthly open source downloads and a fast-growing platform combining LangSmith, open source frameworks, and the newly launched LangSmith Engine, LangChain is positioned at the forefront of the AI agent revolution.

The global AI agent hiring market is experiencing unprecedented growth, with deployment and architecture roles becoming increasingly critical as enterprises move from experimental AI projects into production environments. LangChain is expanding its Professional Services team to meet this demand and help enterprise customers architect and deploy agent systems that drive real business value.

You'll join the Customer Engineering team as a Deployed Architect, taking a hands-on role working directly with enterprise customers to design, deploy, and optimize production-grade AI infrastructure and agent systems. This position blends deep technical expertise in infrastructure engineering with modern agent development practices, requiring you to excel across Kubernetes cluster design, multi-agent system architecture, customer requirement assessment, and best practice development. You'll drive meaningful customer outcomes while shaping how LangChain technology operates in the real world.

What you'll do

• Design and deploy highly available, scalable infrastructure for AI platforms using cloud services (GCP, AWS, or Azure), including Kubernetes cluster architecture, multi-region HA/DR strategies, infrastructure as code with Terraform and Helm, and CI/CD pipeline implementation

• Architect multi-agent systems using various patterns and frameworks, implement agent logic with LangChain and LangGraph, build evaluation frameworks, optimize prompts through A/B testing, and guide customers through deployment and operations

• Lead technical maturity assessments with enterprise customers to understand requirements, present architectural recommendations, and partner with Engagement Managers and internal Product and Engineering teams

• Advise on database design including relational systems, in-memory stores, replication, backup strategies, networking, security protocols (SSO, RBAC, TLS), secrets management, and observability platforms

What you'll bring

• Seven or more years in customer-facing technical roles such as Solutions Architect, Deployed Architect, or Forward Deployed Engineer (founders with equivalent experience also welcome)

• Three or more years designing and deploying production infrastructure on major cloud platforms, with strong Kubernetes expertise (GKE, EKS, or AKS) including cluster design and multi-zone deployments

• One or more years building production AI/ML applications or agents, with strong hands-on experience using LLM frameworks like LangChain or LangGraph

• Demonstrated expertise in state management patterns, evaluation framework design, prompt engineering with optimization techniques, vector stores, RAG patterns, and tool integration patterns

• Strong Python or TypeScript development skills combined with enterprise customer experience and ability to conduct technical assessments

• Consultative mindset with excellent cross-functional collaboration skills and ability to translate complex technical concepts for diverse audiences

What they offer

• Base salary of £100,000 to £165,000 plus equity

• Remote role based in London with up to 25% travel