Search
Go
This job is no longer accepting applications
This listing was closed on Sep 16, 2026.
Browse Open JobsResearch Software Engineer, Safety Evaluations Infrastructure
Summary by AIEngineer.careers
Research Software Engineer, Safety Evaluations Infrastructure is a AI Infrastructure Engineer role (full-time). with Reflection AI. in REMOTE, GREATER LONDON, GB. Imported listing (source: remotefront.com). Apply on the employer's site (remotefront.com).
Imported listing (source: remotefront.com) · Apply on remotefront.com
REMOTE · GREATER LONDON · GB
—
Full-time
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from remotefront.com
Reflection AI is hiring a Research Software Engineer to design and build the secure infrastructure powering its most sensitive model evaluations, including CBRN, child safety, and other dangerous-capability domains. This high-ownership role combines platform engineering, security, and safety research, focusing on sandboxed execution environments, controlled data pipelines, and evaluation orchestration tooling.
Responsibilities
- Design and build secure, sandboxed infrastructure for running sensitive model evaluations, including CBRN and other dangerous-capability domains.
- Build controlled data pipelines and storage for sensitive evaluation material, applying least-privilege, RBAC, encryption, audit logging, and data-minimization safeguards.
- Partner with safety researchers and domain experts to translate evaluation designs into reliable, reproducible, and scalable systems.
- Build eval-orchestration tooling and harnesses for high-throughput evaluations against models and agents in isolated environments.
- Develop infrastructure for measuring AI capability uplift in high-consequence domains and integrate results into release decision pipelines.
- Implement guardrails, monitoring, and compartmentalization across compute, data, and tooling.
- Write production-quality Python for high-throughput data processing and evaluation systems.
Reflection AI
New York · US · 159+ employees
Reflection AI is an artificial intelligence lab focused on building frontier open-weight models and autonomous AI agents. Founded by former researchers from DeepMind, the company aims to provide accessible, high-performance open intelligence for enterprises, governments, and researchers.
