Remote Coding Research & Evaluation Engineer

micro1; United Kingdom; On-site; GBP 133,000 - 192,000; Full time

Benefits offered by this job

Equity compensation

Health insurance reimbursement

Paid time off

401(K) plan with company match

Remote-first workforce

Job summary

micro1 is seeking a highly skilled Member of Technical Staff to advance frontier coding research. You will design evaluation frameworks, benchmarks, and data systems that shape how next-generation coding models are measured and improved in a remote-friendly environment.

You will lead end-to-end research on measuring model performance across software engineering tasks, develop datasets and protocols, and build scalable tooling for large-scale experiments.

Qualifications

• 3+ years in software engineering, ML research, or evaluation.
• Experience designing benchmarks, coding tasks, or evaluation methods.
• Familiar with LLMs, coding agents, or related AI systems.
• Ability to build tooling, automate workflows, and run experiments.
• Excellent written and verbal communication for diverse audiences.

Responsibilities

• Design and own evaluation frameworks for coding agents and benchmarks.
• Lead end-to-end research measuring coding model performance.
• Develop datasets, golden examples, and evaluation protocols.
• Analyze model behavior and identify weaknesses for improvements.
• Build tooling and pipelines to support large-scale experiments.
• Establish best practices for rigorous, reproducible assessments.
• Collaborate with researchers and engineers on experiments.
• Contribute to technical reports and client-facing research.

Skills

Python

C++

Software engineering

Benchmarks

Model evaluation

Analytical thinking

Communication

Tools

Git

PyTorch

Docker

CLI tooling

Job description

micro1 is seeking a highly skilled Member of Technical Staff to advance frontier coding research. You will design evaluation frameworks, benchmarks, and data systems that shape how next-generation coding models are measured and improved in a remote-friendly environment.

You will lead end-to-end research on measuring model performance across software engineering tasks, develop datasets and protocols, and build scalable tooling for large-scale experiments.