Software Engineer, Agent
Build and ship production agent infrastructure and frontend experiences for AI-powered creative products. The role requires full-stack production experience, hands-on LLM agent development, strong data modeling, and familiarity with tool use, planning, memory, and orchestration.
About the job
Responsibilities
- Build and extend the agent harness powering conversational and autonomous creative workflows, including tool use, context and memory management, multi-step planning, and sub-agent orchestration.
- Build and maintain MCP servers and CLI-based agent tooling connecting agents to internal services, external model vendors, and creative asset pipelines.
- Author reusable Agent Skills and structured workflows for complex creative tasks such as scene planning, storyboarding, asset generation, and revision loops.
- Contribute to evaluation frameworks and observability systems to detect regressions and measure agent quality.
- Ship polished production frontend experiences for agent-driven products using React and Next.js.
- Make pragmatic trade-offs among speed, correctness, and scalability and communicate decisions clearly.
- Partner with product, design, and go-to-market teams to translate user needs into technical solutions.
- Track developments in MCP, Agent Skills, and orchestration frameworks.
Requirements
- 2+ years of full-stack engineering experience shipping production software.
- Hands-on experience building LLM-powered agents or applications used by real users.
- Familiarity with agent harness concepts, including tool use, context and memory management, multi-step planning, or sub-agent orchestration.
- Strong data modeling and schema design skills.
- Experience using AI-assisted coding tools such as Claude Code, Codex, or Cursor.
- Strong product sense and the ability to create trustworthy, delightful agent experiences.
- Clear communication skills for explaining agent behavior and technical trade-offs to non-engineers.
Nice to Have
- Experience authoring reusable Agent Skills or structured agent workflows.
- Experience building MCP servers or CLI tooling for agents.
- Exposure to agent orchestration frameworks such as Claude Agent SDK or LangGraph.
- Experience with LLM evaluation or observability tooling.
- Experience with image or video generation models.
- Startup experience or experience building products from 0 to 1.
Compensation and Benefits
- Total compensation of $300,000 or more, including base salary, bonus, and equity.
- Meaningful equity ownership.
- High autonomy and growth opportunities.
- Visa sponsorship available.
Skills
Full-Stack Engineering, Llm Agents, Agent Harnesses, Mcp, Cli Tooling, React, Next.js, Data Modeling, Schema Design, Claude Code, Codex, Cursor, LangGraph, Llm Evaluation, Observability
Similar jobs
Fullstack Engineering jobs
OpenArt
San Carlos, CA
Build the full-stack enterprise platform for an AI creative product, including workspaces, permissions, billing, security, and admin experiences. The role requires 2+ years of production full-stack experience with React/Next.js, Node.js/TypeScript or Python, and relational databases.
Thinking Machines Lab
San Francisco, CA
Build full-stack research infrastructure used to manage training runs, evaluations, experiments, and model visualizations. The role partners closely with researchers and requires strong software engineering fundamentals, cross-stack ownership, and at least two years of post-graduate engineering experience.
Thinking Machines Lab
San Francisco, CA
Build an end-to-end evaluation platform for frontier AI models, spanning backend systems, data pipelines, APIs, and user-facing applications. The role requires software engineering experience, model evaluation expertise, and the ability to collaborate closely with researchers.
Garner Health
New York, NY
Build and maintain AI-enabled software systems for a healthcare technology company, collaborating across disciplines and protecting sensitive user data. The role requires at least two years of software engineering experience, particularly with distributed event-driven architectures.
Applied Intuition
Sunnyvale, CA
Builds and deploys software and machine learning components for behavior prediction, decision-making, and environmental interaction systems. Requires a bachelor’s degree and at least one year of relevant experience with Python, Go or C++, scalable data pipelines, deep learning, and cloud infrastructure.