Senior Backend Engineer (AI Agent)

Commerce; Austin (TX); Hybrid; USD 116,000 - 195,000; Full time

Job summary

Commerce is seeking a Senior Backend Engineer to help build a new team delivering conversational AI agents for the B2B commerce lifecycle. You will design orchestration, sub‑agent architecture, tool integration, prompt engineering, and evaluation disciplines to ensure trustworthy, shipping‑ready agents.

You will collaborate with product and frontend teams to deliver intuitive conversational experiences, prototype proofs of concept quickly, and mentor peers in agent engineering practices while

Qualifications

• 5+ years of backend or full‑stack development with agentic AI/LLM applications.
• Bachelor’s degree in CS/EE/SW/CE/MIS or equivalent experience.
• Strong development skills in Go, Python, Ruby, PHP.

Responsibilities

• Design, build, and iterate on AI agents with orchestrator/sub‑agent architecture.
• Own eval‑driven development with datasets, scorers, and regression suites.
• Develop prompts, model configurations, and versioned artifacts.
• Integrate agents with MCP servers and backend tools with safe tool-call contracts.
• Instrument agents with tracing, metrics, and cost tracking.

Skills

Backend development

Agentic AI/LLM

Go

Python

LLMs in production

Prompt engineering

API design

Distributed systems

Education

Bachelor's degree in CS/EE/SW/CE/MIS

Tools

MCP servers

Google ADK

LangChain/LangGraph

Semantic Kernel

Job description

About the Role

BigCommerce is building a new team to deliver a suite of conversational AI agents spanning the B2B commerce lifecycle—Product Discovery, Pricing & Quoting, Order Automation, Fulfillment & Delivery, and Post‑Sale Support. The agents are built in Go on Google ADK with Gemini, with evaluation infrastructure in Braintrust and 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 these agents are trustworthy enough to ship.

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 critical quality metrics such as discovery recall and quote accuracy.
• Develop and refine prompts, model configurations; treat prompts and model settings 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 and abuse.
• Instrument agents with tracing, metrics, and cost tracking; use production signals to drive quality improvements.
• Collaborate with product designers and frontend engineers to deliver intuitive, useful conversational experiences.
• Quickly build proof‑of‑concept agents to validate user stories, then harden them to GA quality.
• Drive architecture decisions on ambiguous problems and mentor other engineers in agent engineering practices.

Qualifications

• 5+ years of experience in backend or full‑stack software development, with hands‑on experience building agentic AI/LLM applications.
• Education: Preferred minimum Bachelor’s degree in CS, EE, SW, CE, MIS; or equivalent experience.
• Strong and proven development skills in any major language (Go, Python, Ruby, PHP).
• Experience working with LLMs (Gemini, Anthropic, OpenAI, etc.) in production systems.
• Experience with LLM evaluation: building datasets, defining scorers/metrics, and using evaluation 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.
• Excellent problem‑solving skills and ability to work in a fast‑paced, exploratory environment.
• Strong collaboration and communication skills in cross‑functional teams.
• Strong preference toward execution and delivery.

Preferred

• Experience with agent frameworks (Google ADK, LangChain/LangGraph, Semantic Kernel, or similar).
• Experience with evaluation/observability platforms (Braintrust, LangSmith, or similar).
• Experience with RAG systems and retrieval quality tuning.
• Experience with e‑commerce platforms or SaaS product development.
• Background in conversational AI or natural language processing.

Work Where You Thrive

For candidates based in the Austin or Atlanta metro area, the position follows a hybrid work model with three days per week in the office, balancing focused individual work with meaningful in‑person collaboration.

Compensation Transparency

Pay Transparency Range: $116,000.00 – $195,000.00. Final compensation will be determined based on relevant experience, skills, qualifications, geographic location, and internal equity.

Inclusion and Belonging

At Commerce, we believe that celebrating the unique histories, perspectives and abilities of every employee makes a difference for our company, our customers and our community. We are an equal opportunity employer and the inclusive atmosphere we build together will make room for every person to contribute, grow and thrive.