← All roles

Applied Research - Continual Learning

Prime Intellect· Applied Research
Apply on company site
San Francisco, New York, Remote, London$150k - $300kFull-timePosted 5d ago

About the role

Role focused on building continual learning systems that turn agent trajectories, corrections, and failures into new tasks and model updates, evaluating streaming RL, batched post-training, and distillation, and tracking skill acquisition and transfer over long sequences of tasks.

Responsibilities

  • Applied Research at Prime: turn workflows into tasks, environments, evaluations, and reward signals; run post-training experiments against real baselines; deploy what works; identify whether gains come from model, data, harness, inference, or infrastructure; reusable parts become shared research, open-source systems, and product capabilities.
  • Role scope: Control update cadence, policy lag, task drift, and exploration; evaluate each checkpoint on earlier skills, unseen tasks, and general capabilities; build reproducible data and harness pipelines; work with external collaborators whose deployments drive the research.
  • Representative early problems: - Select high-value production traces and interventions; convert to training signal; establish regression gates before deployment. - Determine whether adaptation belongs in model weights, harness state, memory, tools, or data; measure tradeoffs across tasks. - Build evaluations that distinguish retained learning and transfer from memorization, context accumulation, or measurement drift.
  • What you will own: - Methods for selective consolidation, replay, adaptation, memory, and online or offline RL. - Evaluations for retention, transfer, regression, and rollback as tasks/distributions change. - Promotion gates and human oversight for agents changing in production. - Field experiments, benchmarks, and open research for measurable continual improvement.

Qualifications

  • Relevant experience: 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: meaningful baselines, careful trace inspection, clear failure attribution, and willingness to change direction with evidence.
  • Strong Python and ability to build artifacts that other researchers and engineers can run, inspect, and extend.
  • Comfort owning ambiguous problems and keeping partners and teammates current as you resolve them.

Skills

Required:Continual or online learningReinforcement learningExperiment design and analysisPythonAmbiguity tolerance and stakeholder communication

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
Last updated Oct 21, 2026. Interested? Apply on the company site.

About Prime Intellect

Commoditizing Compute & Intelligence

Prime Intellect democratizes AI development at scale. Our platform makes it easy to find global compute resources and train state-of-the-art models through distributed training across clusters. Collectively own the resulting open AI innovations, from language models to scientific breakthroughs.

AI developmentbessemer-ai-infrastructure-2026compute resourcesdistributed trainingmodelsreinforcement-learning-platformsscience
Company profileWebsite

More open roles at Prime Intellect