AI Agent Harness R&D Lead

Stealth Startup; Abu Dhabi; On-site; AED 450,000 - 600,000; Full time

Benefits offered by this job

On-prem Nvidia hardware

Flexible work environment

International, ex-FAANG team

Job summary

Stealth Startup in Abu Dhabi is seeking an engineering leader to set the technical direction of a computer-use AI harness and to design interfaces across abstraction levels. You will drive architecture and evaluation culture in a fast-moving team.

The role focuses on coaching engineers, hiring, and coordinating with product management on the backlog, while ensuring delivery of working software every sprint within an international, ex-FAANG environment.

Qualifications

• Clear written and spoken English; communicates progress to executives.
• 6+ years engineering with 2+ years leading a team.
• Still coding; able to review TypeScript and Python in production.
• Bachelor's degree or proven OSS track record.

Responsibilities

• Set the technical direction of the harness and interfaces between abstraction levels.
• Establish the evaluation regime and fortnightly score; hold team to measured results.
• Run the R&D team on a two-week rhythm: planning, review with working software, retrospective, post-mortems for failed experiments and incidents.
• Coach, level and hire the engineers; interface with product management on the backlog and with the platform team on what the harness exposes.

Skills

Technical leadership

LLM / AI systems

TypeScript

Python

Engineering management

English communication

Education

Bachelor's degree

Open-source contributions

Tools

OpenHands

SWE-agent

Aider

DeepSeek Harness

Hermes Agent

LangGraph

smolagents

Kubernetes

TypeScript

Python

Job description

Stealth Startup in Abu Dhabi is seeking an engineering leader to set the technical direction of a computer-use AI harness and to design interfaces across abstraction levels. You will drive architecture and evaluation culture in a fast-moving team.

The role focuses on coaching engineers, hiring, and coordinating with product management on the backlog, while ensuring delivery of working software every sprint within an international, ex-FAANG environment.