Member of Engineering (Reinforcement Learning Infrastructure)
Poolside, a company building toward AGI by accelerating software development with agentic systems, coding assistants, and the frontier models that power them, is hiring a Member of Engineering for its reinforcement learning team. The team focuses on improving the reasoning and coding abilities of Large Language Models through reinforcement learning. This is a hands-on, end-to-end role spanning research into new exploration or training algorithms, designing and scaling up RL environments, and implementing ideas across the stack, with access to thousands of GPUs. The mission is to build and scale the infrastructure that enables reliable, efficient training of LLMs with RL at the frontier. The team is distributed across Europe and North America, with monthly 3-day in-person gatherings in Paris.
Responsibilities
- ▹Keep up with the latest research and stay familiar with the state of the art in LLMs, RL, and code generation
- ▹Develop methods for tuning training and inference end-to-end for high throughput
- ▹Design data control systems in an RL pipeline that govern what the model sees and when
- ▹Debug cases where infrastructure decisions are silently degrading learning dynamics
- ▹Build observability tooling that surfaces when a system-level issue is the root cause of a training regression
- ▹Help build robust, flexible, and scalable RL pipelines
- ▹Optimize performance across the stack: networking, memory, compute scheduling, and I/O
- ▹Write high-quality, pragmatic code
- ▹Work within the team: plan future steps, discuss, and stay in touch
Requirements
- ▹Experience with LLMs and model post-training workflows
- ▹Understanding of how Reinforcement Learning works and what its main bottlenecks are
- ▹Solid software engineering fundamentals (testing, code review, debugging complex systems)
- ▹Proficiency in Python with knowledge of concurrency, asynchronous programming, multiprocessing, and performance optimization
- ▹Familiarity with deep learning frameworks (PyTorch or JAX) and RL workflows (rollouts, replay buffers, policy updates)
- ▹Experience designing and maintaining distributed RL training systems
- ▹Experience with large-scale LLM training infrastructure
- ▹Experience with profiling tools across the stack (e.g. py-spy)
- ▹Experience with inference stacks (e.g. vLLM)
Nice to have
- ▹Open-source contributions to RL or distributed ML projects
Soft skills
What we offer
- ▹Fully remote work and flexible hours
- ▹37 days/year of vacation and holidays
- ▹Health insurance allowance for you and dependents
- ▹16 weeks of flexible, full-pay parental leave
- ▹Well-being, always-be-learning, and home office allowances
- ▹Company-provided equipment
- ▹Frequent team get-togethers (monthly 3-day gatherings in Paris)
- ▹Diverse and inclusive people-first culture