Staff AI Engineer — Agent Orchestration & Production

deCircle; San Francisco (CA); On-site; USD 225,000 - 350,000; Full time

Benefits offered by this job

Health benefits

Stock options

401(k)

Unlimited PTO

Lunch and dinner onsite

Team events

Pre-tax commuter benefits

Job summary

FurtherAI in San Francisco is seeking a Staff AI Engineer to shape both the product and how FurtherAI builds agents. This role focuses on orchestration and reasoning systems on top of existing LLMs, not model training.

You will set up evals, explore multi-agent strategies, and build production-ready MCP servers and tooling to run agents reliably. Join a team building AI workflows for the insurance domain.

Qualifications

• 8+ years building in ML/AI at a high-growth top tech company.
• Strong experience with Python.
• Amazing ability to speak with LLMs (prompting).
• Clear communicator, both in person and in writing.
• Bonus: background in B2B SaaS and 0-1 experience.

Responsibilities

• Set up end-to-end evals to measure and improve agent performance.
• Experiment with new agentic techniques: multi-agent systems, reasoning-from-feedback, and more.
• Build lightweight tools, servers and orchestration layers (e.g. MCP servers) that let agents run reliably in production.
• Stay on top of emerging research on LLMs/agents and bring ideas into production experiments.

Skills

8+ years ML/AI experience

Python

LLMs prompting

Communication

B2B SaaS background

Job description

FurtherAI in San Francisco is seeking a Staff AI Engineer to shape both the product and how FurtherAI builds agents. This role focuses on orchestration and reasoning systems on top of existing LLMs, not model training.

You will set up evals, explore multi-agent strategies, and build production-ready MCP servers and tooling to run agents reliably. Join a team building AI workflows for the insurance domain.