Deployed Architect, Professional Services (San Francisco)
About this role
LangChain builds the foundation for agent engineering in the real world, developing open-source frameworks and a platform for building, evaluating, deploying, and operating agents at scale. The Professional Services team works directly with enterprise customers to design, deploy, and optimize production-grade AI infrastructure and agent systems.
As a Deployed Architect, the individual will architect scalable, secure infrastructure deployments and build reliable, well-evaluated agent applications that solve real business problems. The position combines software development, infrastructure and platform engineering, and customer-facing responsibilities, ranging from Kubernetes cluster design to multi-agent system architecture. Ideal candidates bring a strong engineering background, enterprise customer experience, and the ability to balance infrastructure architecture with hands-on agent development.
What you will do
- Design scalable and highly available infrastructure for AI platform deployments, incorporating cloud compute, storage, networking, security, Infrastructure as Code, and CI/CD pipelines.
- Architect multi-agent systems using diverse patterns and implement agent logic with modern frameworks like LangChain and LangGraph.
- Build comprehensive evaluation frameworks and optimize prompts through A/B testing while guiding deployment and operations.
- Lead technical maturity assessments and work directly with enterprise customers to understand requirements and present actionable recommendations.
- Partner closely with internal Engagement Managers as well as Product and Engineering teams to drive adoption.
What you need
- Bring seven or more years of experience in technical, hands-on customer-facing roles such as Solutions Architect or Forward Deployed Engineer.
- Possess at least three years of experience designing and deploying production infrastructure on cloud platforms such as GCP, AWS, or Azure.
- Demonstrate strong Kubernetes experience including cluster design, autoscaling, and multi-zone deployments alongside Infrastructure as Code tools like Terraform and Helm.
- Have a minimum of one year of experience building production AI or ML applications or agents using LLM frameworks like LangChain or LangGraph.
- Demonstrate strong development skills in Python and/or TypeScript.
- Show proven customer-facing experience working with enterprise clients to conduct technical assessments or infrastructure audits.
Benefits
- Medical, dental, and vision coverage
- Flexible vacation
- 401(k) plan
- Meals on in-office days in the US
Skills and tech stack
Questions candidates ask
What is the location and travel requirement for this role?
The position is based in San Francisco, California. Candidates should also be willing to travel up to 20% of the time.
What is the compensation range for this position?
The base salary ranges from $170,000 to $215,000, and the role also includes equity. Actual compensation will vary based on role, level, and location.
What technologies and frameworks will I be working with?
You will work with cloud platforms like GCP, AWS, or Azure, Kubernetes, Terraform, Helm, and CI/CD pipelines. For agent engineering, you will use Python or TypeScript alongside LLM frameworks such as LangChain and LangGraph.