Responsibilities
- Design scalable, highly available AI platform infrastructure covering compute, storage, networking, security, enterprise integration patterns, Infrastructure as Code, multi-region high availability and disaster recovery, and CI/CD.
- Design and build multi-agent systems using modern agent frameworks and implement agent logic.
- Create evaluation frameworks, optimize prompts through A/B testing, and guide application deployment and operations.
- Lead technical maturity assessments, understand enterprise customer requirements, and present technical recommendations.
- Partner with Engagement Managers and Product and Engineering teams to guide customer implementations and shape best practices.
Requirements
- At least 7 years of experience in hands-on technical customer-facing roles such as Solutions Architect or Forward Deployed Engineer.
- At least 3 years of experience designing and deploying production infrastructure on GCP, AWS, or Azure.
- Strong Kubernetes experience, including cluster design, autoscaling, and multi-zone deployments, with GKE, EKS, or AKS.
- Experience with Terraform, Helm, GitOps practices, high-availability and disaster-recovery solutions, and infrastructure and application CI/CD pipelines.
- Knowledge of relational databases and in-memory data stores, including high availability, replication, backup strategies, and sizing.
- Strong understanding of networking, security including SSO/RBAC, TLS, and secrets management, and observability using Prometheus, Grafana, or Datadog.
- At least 1 year of experience building production AI/ML applications or agents.
- Strong experience with LangChain, LangGraph, or similar LLM frameworks for agent-based applications.
- Experience with state management, AI application evaluation frameworks, prompt optimization, A/B testing, vector stores, RAG patterns, knowledge organization, tool integration, API design, and error handling.
- Strong Python and/or TypeScript development skills.
- Enterprise customer-facing experience and experience conducting technical assessments or infrastructure audits.
- Strong communication, problem-solving, consultative, and cross-functional collaboration skills.
Benefits
- Remote work available with up to 25% travel.
- UK location in London.
- Medical, dental, and vision coverage.
- Flexible vacation.
- 401(k) plan.
- Meals on in-office days in the US.
- Locally competitive benefits for team members in the EU, UK, and APAC.
Tech Stack
Categories
About LangChain
At LangChain, our mission is to make intelligent agents ubiquitous. We build the foundation for agent engineering in the real world, helping developers move from prototypes to production-ready AI agents that teams can rely on. What began as widely adopted open-source tools has grown into a platform for building, evaluating, deploying, and operating agents at scale. LangChain provides the agent engineering platform and open source frameworks developers need to ship reliable agents fast. LangSmith offers observability, evaluation, and deployment for rapid iteration. Our open source frameworks, LangGraph, LangChain, and Deep Agents, help developers build agents with speed and granular control. LangSmith is trusted by leading AI teams at Zip, Vanta, Klarna, Workday, Linkedin, Cloudflare, and more.