Applied Researcher - Continual Learning

The role

You will build continual learning systems that turn agent trajectories, corrections, and failures into new tasks and model updates. You will compare streaming RL, batched post-training, and distillation to determine improvements for model weights or persistent memory.

What you will do

• Turn workflows into tasks, environments, evaluations, and reward signals
• Run post-training experiments against real baselines and deploy what works
• Work directly with external collaborators whose deployments drive research
• Control update cadence, policy lag, task drift, and exploration
• Build task-generation and training pipelines with reproducible data
• Select high-value production traces and convert them into training signal
• Determine which adaptation belongs in model weights, harness state, memory, tools, or data
• Build evaluations that distinguish retained learning and transfer from memorization
• Develop methods for selective consolidation, replay, adaptation, memory, and RL
• Create promotion gates and human oversight for agents in production

Required qualifications

• Relevant experience in continual or online learning, RL, meta-learning, memory systems, post-training data loops, adaptive production ML, or evaluation under changing distributions
• Hands-on experience building and debugging model-training, post-training, agent, evaluation, or closely adjacent experimental loops
• Strong experimental judgment
• Strong Python
• Ability to build artifacts that other researchers and engineers can run, inspect, and extend
• Comfort owning ambiguous problems

Nice to have

• Publications
• Open-source systems
• Benchmarks
• Shipped products

Benefits

• Cash Compensation Range of $150-300k + equity incentives
• Flexible Work (San Francisco, New York, London, or remote)
• Visa Sponsorship & relocation support
• Professional Development budget
• Team Off-sites & conference attendance

About the company

Prime Intellect is building the open superintelligence stack, providing infrastructure for frontier AI labs. The platform Lab unifies compute, environments, evaluations, secure sandboxes, high-performance training, and deployment.