As an RL Research Engineer, you will own the post-training pipeline for specialist language models that detect security threats in real-time. You will design and ship RL pipelines—including RLHF, DPO, and GRPO—to classify malicious trajectories. Your work ensures autonomous systems are resilient against adaptive attacks, providing critical security infrastructure for enterprise AI.
RL Research Engineer at well-funded cybersecurity AI startup
Are you an RL expert looking to build the front line of AI defense? Join a high-pedigree team in London as an RL Research Engineer and lead the post-training for specialist models that prevent autonomous agent attacks. With a total compensation package up to £350k and significant equity, you will own the end-to-end training infrastructure and help define how the world secures agentic systems. This is a rare opportunity to apply cutting-edge RLHF and DPO techniques to critical security challenges at a top-tier VC-backed startup.
Want to apply for this role?
C
Jack finds you jobs at companies like Confidential company. Talk to Jack to get considered for roles that fit what you're great at.
Location
London, United Kingdom
Compensation
Up to £350k (Including Equity)
Company
Confidential company
Role overview
About the company
Well-funded cybersecurity AI startup
What you will do
- Design and ship RL post-training pipelines such as RLHF, DPO, and GRPO to optimize models for real-time security threat classification.
- Build and maintain scalable training infrastructure end-to-end, including distributed training, evaluation harnesses, and rigorous regression testing.
- Develop custom reward models and preference optimization systems tailored to identifying complex, long-horizon malicious agent trajectories.
Who this is a fit for
- Proven hands-on experience with RL post-training for language models (RLHF, DPO, or similar) in a production or research setting.
- Strong engineering fundamentals with the ability to operate complex training pipelines at scale using PyTorch, JAX, and distributed computing.
- A background in machine learning research, ideally with a PhD or equivalent expertise in optimization, alignment, or reinforcement learning.
===
Why this role is remarkable
- Join a high-pedigree founding team building mission-critical defense infrastructure for the next generation of autonomous AI systems.
- Backed by top-tier VCs, this seed-stage startup addresses the urgent need for adaptive security in an increasingly agent-led threat landscape.
- Take significant ownership as you shape the core detection logic and training infrastructure for a highly technical, high-impact product.
How Jack & Jill work together
I get to know what you’re great at, then find roles you’d never find yourself.Ok, I'll go first. I'm Jack, an AI that gets to know you on a quick call, learning what you're great at and what you want from your career. Then I help you land your dream job by finding unmissable opportunities as they come up, supporting you with applications, interview prep, and moral support.
I recruit from Jack’s network and make the intro when I spot a great match.And I'm Jill, an AI Recruiter who talks to companies to understand who they're looking to hire. Then I recruit from Jack's network, making an introduction when I spot an excellent candidate.
Jack gets to know what you're great at and what you want next, then searches 15 million jobs daily and helps you discover roles at companies like this.
Meet Jack
What happens next?
Jack’s an AI agent for job searching and career coaching. He works for you.
Jill is the AI recruiter working for the company. She recruits from Jack’s network.
If your profile’s a match and Confidential company wants to meet, Jill will make the intro. In the meantime, Jack will send you excellent alternatives.