Deployed Architect, Professional Services (San Francisco)

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. Today, our platform includes LangSmith (Observability, Evaluation, Deployment, Fleet, and Sandboxes), our open source frameworks (LangChain, LangGraph, and Deep Agents), and the LangSmith Engine for autonomous agent improvement.

About the Role

We're looking for a Deployed Architect to join our Professional Services team. You'll work directly with enterprise customers to design, deploy, and optimize production-grade AI infrastructure and agent systems. You'll architect scalable, secure infrastructure deployments and build reliable, well-evaluated agent applications that solve real business problems.

This role combines software development, infrastructure/platform engineering, and customer-facing skills, spanning Kubernetes cluster design to multi-agent system architecture.

Key Responsibilities

• Infrastructure & Platform Engineering: Design scalable, highly-available infrastructure for AI platform deployments (compute, storage, networking, security), enterprise integration patterns, Infrastructure as Code (Terraform, Helm), multi-region HA/DR strategies, and CI/CD pipelines.
• Agent Engineering & Development: Design multi-agent systems using various patterns, implement agent logic using modern frameworks (LangChain/LangGraph), design comprehensive evaluation frameworks, optimize prompts with A/B testing, and guide deployment/operations.
• Customer Engagement & Assessment: Lead technical maturity assessments, work directly with enterprise customers to understand requirements and present recommendations, and partner with Engagement Managers and Product/Engineering teams.

Required Experience

• 7+ years of experience in technical, hands-on customer-facing roles such as Solutions Architect or Forward Deployed Engineer (or former founder with equivalent skillsets).
• Infrastructure & Platform:

- 3+ years of experience designing and deploying production infrastructure on cloud platforms (GCP, AWS, or Azure).
- Strong Kubernetes experience (GKE, EKS, or AKS) including cluster design, autoscaling, and multi-zone deployments.
- Experience with Infrastructure as Code (Terraform, Helm) and GitOps practices.
- Knowledge of database systems (relational databases, in-memory data stores) including HA, replication, backup strategies, and sizing.
- Experience designing high-availability and disaster recovery solutions.
- Strong understanding of networking, security (SSO/RBAC, TLS, secrets management), and observability (Prometheus, Grafana, Datadog).
- Experience with CI/CD pipelines for infrastructure and applications.

• Agent Engineering & Development:

- 1+ years of experience building production AI/ML applications or agents.
- Strong experience with LLM frameworks (LangChain, LangGraph, or similar) for building agent-based applications.
- Experience with state management patterns (short-term and long-term memory).
- Experience designing and implementing evaluation frameworks for AI applications.
- Strong prompt engineering skills with experience in optimization and A/B testing.
- Experience with vector stores, RAG patterns, and knowledge organization.
- Experience with tool integration, API design, and error handling patterns.
- Strong Python and/or TypeScript development skills.

• Customer-Facing:

- Customer-facing experience with enterprise customers.
- Experience conducting technical assessments or infrastructure audits.
- Willingness to travel up to 20% of the time.