Senior Backend Engineer (AI Agent)
$116k - $195k • Remote • United States - Remote • Full-time
Posted 10d ago
Job Location
United States - Remote
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
Commerce is building a new team to deliver a suite of conversational AI agents that will span the B2B commerce lifecycle, from product discovery to post-sale support. These agents are being built on Google ADK with Gemini, featuring evaluation infrastructure in Braintrust and a streaming AG-UI frontend. As a Senior Backend Engineer specializing in AI agents, you will be instrumental in designing these agents, focusing on orchestration, sub-agent architecture, tool integration, prompt engineering, and establishing a robust evaluation discipline to ensure agent trustworthiness. Your work will be critical in ensuring agent quality through rigorous evaluation, making this a key ownership area for the team.
Responsibilities
- Design, build, and iterate on AI agents using an orchestrator/sub-agent architecture in Go/Python, covering intent interpretation, delegation, and safe action execution.
- Own eval-driven development by building and maintaining golden datasets, scorers, and regression suites for critical quality metrics.
- Develop and refine prompts and model configurations, treating them as versioned, tested artifacts.
- Integrate agents with MCP servers and backend tools, defining safe tool-call contracts, approval flows, and guardrails.
- Instrument agents with tracing, metrics, and cost tracking, using production signals to drive quality improvements.
- Collaborate with product designers and frontend engineers to deliver intuitive conversational experiences.
- Build proof-of-concept agents to validate user stories and harden them to production quality.
- Drive architecture decisions for ambiguous problems and mentor other engineers in agent engineering practices.
Requirements
- 5+ years of experience in backend or full-stack software development.
- Hands-on experience building agentic AI/LLM applications.
- Strong development skills in a major language like Go, Python, Ruby, or PHP.
- Experience working with LLMs (Gemini, Anthropic, OpenAI, etc.) in production systems.
- Experience with LLM evaluation, including building datasets and defining metrics.
- Strong understanding of prompt engineering, tool/function calling, and agent orchestration patterns.
- Deep experience designing and building APIs (gRPC, GraphQL, REST) and integrating data across systems.
- Hands-on experience building MCP servers or LLM tool integrations.
- Excellent problem-solving skills and ability to work in a fast-paced, exploratory environment.
- Strong collaboration and communication skills in cross-functional teams.
Benefits
- Equity
- Health insurance
- PTO