Senior Backend Engineer, AI Agents & Orchestration

Commerce.com US, Inc.; Austin (TX); Hybrid; USD 116,000 - 195,000; Full time

Benefits offered by this job

Hybrid work model

Competitive compensation

Job summary

Commerce.com US, Inc. seeks experienced engineers to build AI agents for the B2B commerce lifecycle. You will design, implement, and improve agent architectures, prompts, and tool integrations, with a focus on safe, scalable deployments.

You will work with Go and Python, building eval datasets and metrics, and collaborating with product and frontend teams to deliver valuable conversational experiences. Hybrid work in Austin is available.

Qualifications

• 5+ years in backend or full‑stack development with hands‑on agentic AI/LLM experience.
• Bachelor's degree in CS/EE/SW/CE/MIS or equivalent experience.
• Strong skills in Go, Python, Ruby or PHP and API design.

Responsibilities

• Design, build, and iterate on AI agents in Go/Python using an orchestrator/sub-agent architecture.
• Own eval-driven development: golden datasets, scorers, and regression suites for quality metrics.
• Develop and refine prompts, model configurations; treat prompts and model settings as versioned artifacts.
• Integrate agents with MCP servers and backend tools, defining safe tool-call contracts and guardrails.
• Instrument agents with tracing, metrics, and cost tracking; drive quality improvements with production signals.
• Collaborate with product designers and frontend engineers to deliver intuitive conversational experiences.
• Quickly build proof-of-concept agents, then harden them to GA quality.
• Drive architecture decisions on ambiguous problems and mentor other engineers.

Skills

Backend development

Full-stack development

Agentic AI/LLM apps

Go

Python

API design

Education

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

Tools

MCP servers

LLM tool integrations

Job description

Commerce.com US, Inc. seeks experienced engineers to build AI agents for the B2B commerce lifecycle. You will design, implement, and improve agent architectures, prompts, and tool integrations, with a focus on safe, scalable deployments.

You will work with Go and Python, building eval datasets and metrics, and collaborating with product and frontend teams to deliver valuable conversational experiences. Hybrid work in Austin is available.