Software Engineer, AI Automation

What you'll do

• Translate business processes into reusable agent skills; connect agents to systems of record using MCP and build workflows.
• Define and build evaluation sets, establish baselines, and use results to guide deployment decisions.
• Take agents from prototype to production, supporting permissions, human review, audit trails, rollback, tuning, and handoff.

What they ask for

• Substantial hands-on experience shipping LLM-backed applications, including prompting, tool use, agentic loops, and multi-step workflows; at least one agent used by non-engineers.
• Practical experience with MCP, authoring skills or tools, and orchestrating agents against systems of record; experience building eval sets and using them to make decisions.
• Strong Python; comfortable with SQL and production data models; fluent with agentic coding tools such as Cursor.
• At least 5+ years of hands-on software development experience; able to translate non-technical operators’ processes into requirements and deploy and maintain work using Git, CI, and containers.

Nice to have

• Experience building or maintaining MCP servers; solutions engineering, professional services, internal tools, or startup founding experience.
• Working knowledge of Linear, Jira, Zendesk, Salesforce, or Snowflake; experience in insurance, fintech, or another regulated domain.

Pay

USD 115,000/year–USD 168,000/year base salary

Tools

LLMs, MCP, Cursor, Python, SQL, Git, CI, containers

AI focus

Build and operate LLM-powered agents to automate internal workflows, including agent skills, integrations, evaluations, production deployment, and ongoing tuning.