Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Research Engineer - Post-Training role.
Rezi rewrites your resume against Pluralis Research's job description. Free.
Tailor your resume to this Research Engineer - Post-Training role.
Rezi rewrites your resume against Pluralis Research's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Research Engineer - Post-Training posting at Pluralis Research — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Research Engineer - Post-Training posting at Pluralis Research — free, in seconds.
About the Role
Pluralis Research is pioneering Protocol Learning, enabling decentralized training and serving of large models on consumer devices. This role focuses on making RL post-training work within a unique, decentralized system, adapting algorithms and building the end-to-end stack for decentralized model releases.
Responsibilities
- Build the RL training loop end-to-end, including rollout ingestion, reward computation, policy updates, and weight distribution.
- Adapt standard RL algorithms for asynchronous, high-latency, and partially trusted generation environments.
- Develop evaluation metrics to demonstrate model improvement.
- Manage the release of the first decentralized post-trained models from development to public artifact.
Requirements
- Hands-on experience with RL post-training on large language models (RLHF, RLVR, or reasoning-focused RL).
- Experience with the systems layer of RL post-training, including rollout generation, asynchronous training loops, and weight synchronization.
- Production-quality Python and PyTorch skills, including concurrency, failure handling, and performance profiling.
- Ability to defend research work, demonstrated through publications or detailed unpublished work.
- Alignment with the mission of Protocol Learning for collective, trustless, and sovereign AI.
- Professional-level English proficiency (written and spoken).
Skills
- RL post-training
- Large language models
- RLHF
- RLVR
- Reasoning-focused RL
- Systems engineering
- Rollout generation
- Asynchronous training loops
- Weight synchronization
- Python
- PyTorch
- Concurrency
- Failure handling
- Performance profiling
- Research
- Algorithm adaptation
- Decentralized systems
- Federated learning
- Reward modeling
- P2P networking
- NAT traversal
Location
- Remote
- Australia
- North America
- US
Work Type
- Remote-First
- Full-time
Experience Level
- Senior
Salary/Compensations
- High base salary
Benefits
- Significant ownership (equity)
- Flexible work environment
- Optional full visa sponsorship
- Relocation support
About the Company
- Pluralis Research is developing Protocol Learning, a novel approach to decentralized training and serving of large AI models on consumer devices.
- The company has achieved significant advances, including the Agora run which pretrained an 8B model from scratch on distributed consumer GPUs.
- Pluralis is backed by Union Square Ventures and other tier-1 investors.
- The team consists of world-class, deeply technical ML researchers.
- Pluralis is ideologically driven, believing Protocol Learning offers a better path for AI development.