Research Engineer - Post-Training
Pluralis Research · Remote · San Francisco · Australia ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Fully remote (global)
- RL + PyTorch
- Visa sponsorship
- Senior level
- Decentralized AI
You will develop the end-to-end reinforcement learning stack for post-training large models across distributed consumer devices. The work requires inventing algorithms that handle staleness and off-policy corrections in untrusted, high-latency networks.
The team focuses on Protocol Learning, aiming to make pretrained models useful for agentic use cases without relying on traditional datacenter infrastructure. You will ship the first decentralized post-trained releases and define evaluation metrics.
What you'll do
- Build the end-to-end RL training loop including rollout ingestion and policy updates
- Adapt standard RL recipes for asynchronous and high-latency generation environments
- Implement staleness tolerance and communication-efficient policy update mechanisms
- Create evaluation frameworks to demonstrate model improvement over time
- Ship the first decentralized post-trained model releases as public artifacts
What you'll need
- Hands-on experience running RL post-training on large language models
- Proficiency in production-quality Python and PyTorch with concurrency skills
- Experience with system layers like rollout generation and weight synchronization
- Strong research background in RL, asynchronous training, or distributed systems
- Professional-level written and spoken English proficiency
Nice to have
- Experience training models over slow networks or in federated setups
- Familiarity with serving-engine internals such as vLLM or SGLang
- Background in reward modeling or building verifiable-reward datasets
- Knowledge of P2P networking and NAT traversal techniques
- Previous work at proprietary, open-weight, or open-source AI labs
Stack
- Python
- PyTorch
- vLLM
- SGLang
How you'll work
- Fully remote with team members distributed globally
- Main teams located in Australia and North America
- Requires comfort working across multiple time zones
What you get
- Equity-heavy package with significant ownership opportunities
- High base salary for key technical contributors
- Optional full visa sponsorship for Australia or the US
- Relocation support provided if moving to sponsored locations