Research Engineering Manager, AI Agent Harness (Product R&D)

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

THE TECHNICAL CHALLENGE

KEY RESPONSIBILITIES

• Set the technical direction of the harness and the interfaces between its levels of abstraction
• Establish the evaluation regime and the fortnightly score, and hold the team to measured results
• Run the R&D team on a two-week rhythm: planning, review with working software, retrospective, written 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

DESIRED QUALIFICATIONS

• Managed both a research-cadence team and a sprint-cadence team, and can articulate the interface between them
• Built an agent harness or an evaluation harness for computer-use systems, agents or reinforcement learning, with an evaluation culture recognised outside the team, and can say which abstraction was right and which was wrong
• Has taken apart the harnesses of coding agents (OpenHands, SWE-agent, Aider, DeepSeek Harness or comparable) and can explain how they work in plain terms
• Has fine-tuned an LLM, from data preparation to evaluation on a held-out set

EXPECTED QUALIFICATIONS

• T-shaped: deep in one domain, with working breadth in a neighbouring one
• Structures a large, incompletely specified problem and drives it to a working result independently
• Managed a team building on LLMs or machine-learning models in production, with evaluation pipelines as a management requirement and a clear account of how quality was gated
• Turns research or prototype code into reference implementations others reuse, using AI coding tools daily and verifying their output

HOW WE WORK

• Product engineering: we own what we build and run it in production
• Small teams, two-week cycles, working software at every review
• AI coding tools are part of the standard workflow

WHAT WE OFFER

• AI-augmented engineering environment
• Access to on-premise Nvidia B200s
• Flexible work environment

PROCESS

• Practical session; the format is agreed with you

In coding exercises, AI tools are allowed and expected. No LeetCode.

WHO WE ARE

New product organisation as part of a large semi-government in Abu Dhabi. International, ex-FAANG team. Completely greenfield, with a modern tech stack.

REQUIREMENTS TO BE CONSIDERED

• Clear written and spoken English; has reported technical progress to non-technical executives on a fixed cadence
• 6+ years in engineering, of which 2+ leading a team of engineers where work was accepted on measured results
• Still coding, able to review TypeScript and Python; own code operated in production at a product company or a startup
• Bachelor's degree in any field, or self-taught with a track record of open-source contributions

RELATED TECHNOLOGIES AND CONCEPTS

• Agent harnesses and frameworks: OpenHands, SWE-agent, Aider, DeepSeek Harness, Hermes Agent, LangGraph, smolagents
• Programmatic prompt and pipeline optimisation: DSPy, TextGrad, Ax
• Evaluation and observability: evaluation harnesses, LLM-as-judge, trajectory evaluation, Inspect, Langfuse, OpenTelemetry; benchmarks such as Online-Mind2Web, WebArena, OSWorld
• Models and serving: open-weight LLMs, vLLM, SGLang
• State and orchestration: state machines, event sourcing, XState, Trigger.dev, Temporal, Kubernetes, TypeScript, Python