Staff AI Engineer – Agentic Systems & Engines

Hone; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Equity

Relocation support

Visa sponsorship

Job summary

Hone is hiring to build AI engines that own outcomes, not tasks, and continuously improve over weeks and months. You will own how engines learn from feedback, including offline evals, simulations, memory, and the self-improvement loops that update skills, memory, code and policies.

You’ll contribute to production-ready evals and rigorous experimentation for robust AI systems. Join a mission-driven team that ships real-world AI agents, with in-person collaboration in San Francisco and a pathway

Qualifications

• 2+ years of engineering experience or equivalent depth from research, open source or own projects.
• Time at a fast-growing startup.
• Shipped applied ML systems from scratch as an engineer, not only papers.
• Ran evals and experiments rigorously against production systems.
• Strong fundamentals: ML evaluation, experimental design, statistics, LLM agents.
• You use coding agents every day and understand every line you ship.
• You build and tinker for fun because you genuinely care about how the technology works.

Responsibilities

• Simulations built from company context with simulated users and connectors to evaluate engines on tasks that take weeks or months.
• Turning production traces into simulations that we can rewind, fork with one change, and run forward, keeping the simulated world consistent.
• Memory systems that store, retrieve, and compact what engines learn.
• Self-improvement loops that turn traces into verified changes to skills, memory, code and policies.
• Grading and credit assignment over month-long trajectories.

Skills

Engineering experience

ML systems

Experimentation

LLM agents

Coding in production

Fun with tech

Tools

Python

Job description

Hone is hiring to build AI engines that own outcomes, not tasks, and continuously improve over weeks and months. You will own how engines learn from feedback, including offline evals, simulations, memory, and the self-improvement loops that update skills, memory, code and policies.

You’ll contribute to production-ready evals and rigorous experimentation for robust AI systems. Join a mission-driven team that ships real-world AI agents, with in-person collaboration in San Francisco and a pathway