Senior Applied AI Engineer - Agent Harness (Equity 1-2%)

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

Benefits offered by this job

Meals in office

Health insurance

Unlimited PTO

Job summary

Init Intelligence in San Francisco is seeking a Senior/Staff Applied AI Engineer to build and own the agent harness that turns model capability into reliable IT workflows. You will design the execution loop, tool-use strategies, context construction, and model-facing experimentation, while iterating across real customer scenarios.

You will own the boundary between runtime model decisions and deterministic, compiled execution, perform robust evaluations against realistic environments, and improve

Qualifications

• Experience with agent frameworks or tool-using LLM systems.
• Strong programming in Python or TypeScript; comfortable with modern AI tooling.
• Experience with model evaluation, fine-tuning, or prompt design.
• Ability to own systems end-to-end and debug across the stack.
• Think in terms of systems and user outcomes, not just model metrics.
• Enjoy debugging messy, real-world failures and turning them into improvements.
• Willingness to work in SF in-person, Monday to Friday, startup pace.

Responsibilities

• Develop and maintain the core agent harness (execution loop, tool-use strategies, context construction, model-facing experimentation).
• Iterate on agent behaviors across real customer workflows and long-horizon tasks.
• Define the boundary between runtime model decisions and deterministic, compiled execution.
• Run ev al s against replicas of real customer environments and improve robustness.
• Analyze production failures and drive robustness improvements across model, prompts, tools, and environment state.
• Extend computer-use to API-less systems with production guarantees (per-task microVMs, credentials, full action recording).
• Build feedback loops and data systems to improve evaluation and training data.

Skills

Agent frameworks

Tool-using LLMs

Python

TypeScript

Model evaluation

Prompt design

Full-stack ownership

Systems thinking

Debugging real-world failures

Education of users through systems

Job description

Init Intelligence in San Francisco is seeking a Senior/Staff Applied AI Engineer to build and own the agent harness that turns model capability into reliable IT workflows. You will design the execution loop, tool-use strategies, context construction, and model-facing experimentation, while iterating across real customer scenarios.

You will own the boundary between runtime model decisions and deterministic, compiled execution, perform robust evaluations against realistic environments, and improve