Founding RL Researcher: Build Real-World Agents

Zealous Agency; England; On-site; GBP 90,000 - 180,000; Full time

Job summary

Zealous Agency seeks a Founding RL Researcher to lead research and help build novel algorithms and gym environments for training autonomous agents. You will influence technical direction from day one and collaborate directly with experienced second-time founders in a well-funded AI research setting.

The role focuses on reinforcement learning, real-world RL environments, and distributed, large-scale training using Python and PyTorch, with a track record from top labs or companies and publications

Qualifications

• Strong background in reinforcement learning.
• Experience designing or building RL environments grounded in real-world workflows.
• Distributed training at scale.
• Python and PyTorch.
• Experience at a top-tier AI lab or company.
• Publications at top ML conferences, nice to have.

Responsibilities

• Lead efforts to research and help build novel algorithms for training autonomous agents.
• Develop RL environments grounded in real-world workflows.
• Influence technical direction from day one and collaborate with the founding team.
• Publish and present results to major AI labs and researchers.

Skills

Reinforcement learning

RL environments

Distributed training

Python

PyTorch

Top AI lab experience

Publications in ML conferences

Tools

OpenAI Gym

Job description

Zealous Agency seeks a Founding RL Researcher to lead research and help build novel algorithms and gym environments for training autonomous agents. You will influence technical direction from day one and collaborate directly with experienced second-time founders in a well-funded AI research setting.

The role focuses on reinforcement learning, real-world RL environments, and distributed, large-scale training using Python and PyTorch, with a track record from top labs or companies and publications