Backend AI Orchestration Engineer (Equity)

Raydar; San Francisco (CA); On-site; USD 200,000 - 300,000; Full time

Benefits offered by this job

Equity

On-site in San Francisco

Health, dental and medical coverage

Job summary

Raydar is seeking a Backend Software Engineer in San Francisco to design and build the core execution layer of an AI-driven product. You will implement a runtime that coordinates model calls, tool invocations, retries, and state handling across long-running, multi-step jobs, bridging software agents and external tools.

You will wrap scientific engines and data stores behind robust interfaces and contribute to evaluation harnesses and pipelines.

Qualifications

• 2–6 years of professional software engineering experience.
• Strong Python production experience.
• Experience with AI model orchestration and multi-component systems.
• Experience with monitoring and testing tools for language-model systems.
• Ability to learn new scientific domains from domain experts.

Responsibilities

• Build a runtime that coordinates model calls, tool invocations, retries, checkpoints and handoffs across long-running multi-step jobs.
• Structure multi-step processes as graphs linking software agents, external tools and decision points.
• Wrap external engines, data stores and lab systems behind robust interfaces.
• Create evaluation harnesses and testing suites to measure outcomes at user task level.
• Help set team coding norms and contribute to public code when suitable.

Skills

Python

System orchestration

ML/AI workflows

Data management

Monitoring & testing tools

Parallel execution

Education

Master’s degree in CS/Engineering

PhD welcome

Tools

Docker

Kubernetes

Job description

Raydar is seeking a Backend Software Engineer in San Francisco to design and build the core execution layer of an AI-driven product. You will implement a runtime that coordinates model calls, tool invocations, retries, and state handling across long-running, multi-step jobs, bridging software agents and external tools.

You will wrap scientific engines and data stores behind robust interfaces and contribute to evaluation harnesses and pipelines.