Senior Backend Engineer for AI Agent Orchestration

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

Job summary

Commerce is building a new team to deliver conversational AI agents across the B2B commerce lifecycle. As a Senior Backend Engineer, you will design agents, orchestrate sub-agents, and own the evaluation discipline to ensure trustworthy deployment.

You will work with Go/Python, integrate with MCP servers, and collaborate with product and frontend teams to ship high-quality AI-driven experiences.

Qualifications

• 5+ years of backend or full-stack software development experience with hands-on experience building agentic AI/LLM applications.
• Bachelor's degree in CS, EE, SW, CE, MIS or equivalent experience.
• Strong development skills in Go and/or Python; production experience with LLMs.
• Deep understanding of prompt engineering, tool calls, and agent orchestration patterns.

Responsibilities

• Design, build, and iterate on AI agents in Go/Python using an orchestrator/sub-agent architecture.
• Own eval-driven development: create datasets, evaluators, and regression suites for key metrics such as discovery recall and quote accuracy.
• Develop and refine prompts, model configurations; treat prompts as versioned artifacts.
• Integrate agents with MCP servers and backend tools with safe tool-call contracts and guardrails.
• Instrument agents with tracing, metrics, and cost tracking to drive quality improvements.
• Collaborate with product designers and frontend engineers to deliver intuitive conversational experiences.
• Prototype quickly and mature to GA quality.
• Drive architecture decisions and mentor other engineers in agent engineering practices.

Skills

Backend development

LLM integration

Go

Python

Ruby

PHP

Education

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

Tools

gRPC

GraphQL

REST

MCP servers

Braintrust

Job description

Commerce is building a new team to deliver conversational AI agents across the B2B commerce lifecycle. As a Senior Backend Engineer, you will design agents, orchestrate sub-agents, and own the evaluation discipline to ensure trustworthy deployment.

You will work with Go/Python, integrate with MCP servers, and collaborate with product and frontend teams to ship high-quality AI-driven experiences.