Senior AI Engineer – Harness Engineering (Kimchi)

About the Position

We are looking for a Senior AI Engineer to join our Harness Engineering (Kimchi) team at CAST AI. Kimchi is the AI platform inside CAST AI, focusing on building the execution layer where agents do real work. Our infrastructure includes multi-model inference with intelligent routing, an OpenAI-compatible API, and deployment flexibility. This role sits on top of our inference layer, focusing on coding agents, agent runtimes, orchestration systems, and reliability engineering.

Responsibilities

• Build and evolve the agent harness: Ship hooks, permission gates, and context compaction. Every constraint in our system prompt traces to a failure you personally diagnosed.
• Own long-horizon execution: Ensure multi-session task completion via spec-driven prompting, worktree-per-slice git, Ralph loop recovery, and stuck detection. Your completion rate is your metric.
• Architect planner/executor/evaluator pipelines: Plan with a reasoning model, execute with a fast one, and evaluate with a third. Avoid self-verification.
• Manage agent memory and context: Ensure state persistence across sessions, context compaction, and tool-call offloading. Achieve zero context rot on multi-day work.
• Own the harness surface: Develop CLI, TUI, MCP integrations, sandboxed execution, and telemetry. TypeScript on the surface, Go where it matters.

Requirements

• Experience with AI coding agents in production, not just demos.
• Strong proficiency in TypeScript or Go in production. Comfort moving between them.
• Ability to think in harness terms and address agent failures with context and constraints.
• Experience driving features end-to-end: design, build, ship, measure, and iterate.

We Offer

• Competitive salary (€6,500 – €9,000 gross, depending on the level of experience).
• Flexible, remote-first global environment.
• Collaborate with a global team of cloud experts and innovators.
• Equity options.
• Quick feedback with a fast-paced workflow.
• 10% of your work time for personal projects or self-improvement.
• Learning budget for professional and personal development.
• Annual hackathon to spark new ideas and strengthen team bonds.
• Team-building budget and company events.
• Equipment budget to ensure you have everything you need.
• Extra days off to maintain a healthy work-life balance.

About the Company

Kimchi is the AI platform inside CAST AI, focusing on building the execution layer where agents do real work. Our infrastructure includes multi-model inference with intelligent routing, an OpenAI-compatible API, and deployment flexibility. We control the cost curve from GPU placement across clouds to the inference endpoint your agent calls. We treat agent failures as configuration problems, not model problems, and our harness-first thesis has shown a 40%+ improvement in completion rates on internal benchmarks.

This is a location-specific opportunity. We are currently accepting applications from candidates residing in the following European countries: Bulgaria, Croatia, Estonia, Greece, Hungary, Latvia, Lithuania, Poland, Romania, Slovakia, Slovenia, and Ukraine.

As part of our standard hiring process, we would like to inform you that a background check may be conducted at the final stage of recruitment through our third-party provider, Checkr.

Please note that Cast AI does not provide any form of visa sponsorship/work permit.