Remotely
crmpythonsqltypescriptllmagentevaluationmcp
Job Description
📋 Description
- Build autonomous agents for end-to-end GTM motions (inbound, outbound, pipeline, engagement)
- Design human oversight: approval gates, handoffs, escalation paths
- Develop evaluation frameworks for agent behavior in development and production
- Instrument production observability and tie agent actions to pipeline/revenue
- Ship MCP servers, agent skills, and web apps connecting to CRM and data warehouse
- Set technical direction for building, evaluating, and operating agents
🎯 Requirements
- Strong programming in Python or TypeScript; production apps exp.
- Production experience with LLMs: context engineering, agent/MCP development, tool use, evaluation
- Experience with evals and transcript analysis to improve LLM systems
- Working fluency with data, including SQL
- Ability to navigate ambiguity and ship without a spec
- Passion for safe, beneficial AI and user care
🎁 Benefits
- Visa sponsorship available where possible
- Competitive compensation and benefits
- Flexible hours and collaborative office space in SF
- Equity donation & generous vacation/parental leave
Back to all jobs
