Senior Backend Engineer (AI Agent)

About the role

BigCommerce is building a new team of conversational AI agents covering the B2B commerce lifecycle (Product Discovery, Pricing & Quoting, Order Automation, Fulfillment & Delivery, Post-Sale Support). The agents are built in Go on Google ADK with Gemini, evaluated with Braintrust and exposed through a streaming AG-UI frontend. As a Senior Backend Engineer specializing in AI agents, you will design the agents themselves: orchestration, sub-agent architecture, tool integration, prompt engineering and the evaluation discipline that determines whether they are trustworthy enough to ship.

Key responsibilities

• Design, build and iterate on AI agents in Go/Python using an orchestrator/sub-agent architecture, covering intent interpretation, delegation and safe action execution.
• Own eval-driven development: build and maintain golden datasets, scorers and regression suites (Braintrust or similar) for metrics such as discovery recall and quote accuracy.
• 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 for write actions and guardrails against prompt injection.
• Instrument agents with tracing, metrics and cost tracking, using production signals to improve quality.
• Work with product designers and frontend engineers to deliver usable conversational experiences, and quickly build proof-of-concept agents before hardening them to GA quality.
• Drive architecture decisions on ambiguous problems and mentor other engineers in agent engineering practices.

Required profile

• 5+ years of backend or full-stack development experience, with hands-on experience building agentic AI/LLM applications.
• Preferred: Bachelor's degree in CS, EE, SW, CE, MIS or equivalent experience.
• Experience working with LLMs (Gemini, Anthropic, OpenAI, etc.) in production systems.
• Experience with LLM evaluation: building datasets, defining scorers and metrics, and using eval results to drive iteration.
• 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.
• Strong problem-solving, collaboration and communication skills in cross-functional teams, with a strong preference for execution and delivery.

Required skills

• Development in a major language (Go, Python, Ruby or PHP).
• Preferred: agent frameworks (Google ADK, LangChain/LangGraph, Semantic Kernel), evaluation/observability platforms (Braintrust, LangSmith), RAG systems and e-commerce or SaaS product experience.

What we offer

• Remote-first work, with optional collaborative workspaces for team members in Austin, Atlanta and London.
• National base salary range of $116,000 to $195,000, depending on experience, skills and location.