Fullstack Software Engineer, Applied AI

LangChain LangChain · Data AI · San Francisco, CA · Engineering

Fullstack Software Engineer, Applied AI at LangChain, focusing on building and deploying production-grade AI agents and workflows across various business domains. The role involves designing agent architectures, evaluation pipelines, and translating AI research into practical solutions, contributing to the open-source ecosystem. Requires experience shipping AI/ML applications, particularly LLM systems in production, and understanding of agent components like prompting, retrieval, orchestration, and inference.

What you'd actually do

  1. Design, implement, and deploy end-to-end AI workflows and agents that solve real problems across multiple business domains.
  2. Develop and iterate on agent architectures, evaluation pipelines, and performance frameworks to ensure reliability and measurable outcomes.
  3. Translate emerging AI research and tooling into practical, production-ready solutions.
  4. Communicate technical decisions, trade-offs, and insights clearly to both technical and non-technical stakeholders.
  5. Collaborate cross-functionally embedding with teams like Marketing, GTM, Recruiting, or Product to identify opportunities for agent-driven automation and measurable business impact.

Skills

Required

  • Python or TypeScript
  • experience shipping AI or ML-powered applications
  • at least 1 year building LLM systems in production
  • implementing evaluation and monitoring systems for agents or workflows
  • deep understanding of prompting, retrieval, orchestration, inference APIs, and model selection
  • excellent communication skills

Nice to have

  • LangChain or LangGraph expertise
  • experience building or maintaining open source projects
  • background in applied AI research or agentic workflow development

What the JD emphasized

  • production-grade agents, workflows, and applications
  • agent architectures, evaluation pipelines, and performance frameworks
  • emerging AI research and tooling
  • AI or ML-powered applications
  • LLM systems in production
  • evaluation and monitoring systems for agents or workflows
  • prompting, retrieval, orchestration, inference APIs, and model selection

Other signals

  • building production-grade agents, workflows, and applications
  • develop and iterate on agent architectures, evaluation pipelines, and performance frameworks
  • translate emerging AI research and tooling into practical, production-ready solutions
  • contribute to the LangChain and LangGraph ecosystem