Production AI Agent Engineer

OpenTalent; Phoenix (AZ); On-site; USD 120,000 - 180,000; Full time

Job summary

LangChain is seeking a Deployed Engineer to work with customer engineering teams on building and operating AI agents in production. You will co-develop production-grade agents, run pre-sales POCs, and guide customers through architecture decisions with a focus on reliability and scalability.

You will collaborate across engineering, product, and GTM functions, contributing to patterns and code that scale across customers. Travel up to 40% will be required to support deployments.

Qualifications

• 3+ years in a relevant technical role (software engineering, customer engineering, solutions engineering)
• Experience designing agent-based or LLM-powered applications
• Comfortable working directly with customers during POCs and architecture reviews
• Ability to explain technical tradeoffs clearly and build trust with developers
• Bias toward action and solving production problems, not just demos
• Experience operating AI agents in production and performing post-sale advisory work

Responsibilities

• Co-architect and co-build production AI agents with customer engineering teams
• Own the technical win in pre-sales by designing POCs and guiding evaluations
• Help customers deploy and operate agent-based applications
• Advise customers on architecture, best practices, and roadmap decisions
• Run technical demos, trainings, and workshops for developers
• Surface feedback and contribute reusable patterns and sample code
• Occasionally contribute code upstream to improve customer outcomes
• Travel up to 40% to customer sites for deployment and onboarding

Skills

Python

JavaScript

Agent-based apps

LLM-powered

Customer engagement

Production systems

System design

Tools

LangChain

LangGraph

Kubernetes

Job description

LangChain is seeking a Deployed Engineer to work with customer engineering teams on building and operating AI agents in production. You will co-develop production-grade agents, run pre-sales POCs, and guide customers through architecture decisions with a focus on reliability and scalability.

You will collaborate across engineering, product, and GTM functions, contributing to patterns and code that scale across customers. Travel up to 40% will be required to support deployments.