Remote AI Harness Engineer for Autonomous Agents

McGregor Boyall; España; Presencial; EUR 90.000 - 130.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Remote-first

Descripción de la vacante

McGregor Boyall is seeking an AI engineering lead to build a harness for AGI-level models and to collaborate with founders on rapid feature delivery. You will own the autonomous agent runtime, prompts, memory, and evaluation infrastructure, shaping how tools and skills interact in complex tasks.

This remote-first role offers global hubs and direct impact on product reliability and user value, with opportunities to influence strategic decisions and scale at pace.

Formación

• Proven experience building or modifying AI agent harnesses.
• Deep understanding of how system prompts, skills, and tools interact in complex scenarios.
• Experience creating custom skills, commands, CLIs, or MCP servers for agentic coding.
• Proficiency in agentic coding and stress-testing models and harnesses.
• Strong systems thinking with ability to trade off and design for scale.
• Fast-paced work ethic with a focus on immediate shipping.
• Genuine interest in AI, with reading relevant papers and forming opinions on evaluations.

Responsabilidades

• Build the agent runtime: Develop the loop where the agent plans, acts, and verifies its own work.
• Engineer the context: Shape how system prompts, skills, memory, and tools interact on complex problems.
• Enhance tool fluency: Integrate various tools and ensure the agent can recall and use the right functions.
• Expand agent capabilities: Develop reliable memory, self-written skills, and autonomous work execution.
• Improve performance: Conduct evaluations, catch regressions, and turn failures into fixes.
• Ship product features: Deliver features to users via platforms like Slack and Teams within hours.

Conocimientos

AI agent harnesses

system prompts interactions

custom skills/commands/CLIs

agentic coding

stress-testing models

systems thinking

fast-paced shipping

reading papers & evaluations

MCP servers

CLI development

Herramientas

MCP servers

CLI development

Descripción del empleo

McGregor Boyall is seeking an AI engineering lead to build a harness for AGI-level models and to collaborate with founders on rapid feature delivery. You will own the autonomous agent runtime, prompts, memory, and evaluation infrastructure, shaping how tools and skills interact in complex tasks.

This remote-first role offers global hubs and direct impact on product reliability and user value, with opportunities to influence strategic decisions and scale at pace.