Applied Research - Continual Learning

Skills

About the Role

You will build continual learning systems that transform agent trajectories, corrections, and failures into tasks and model updates. You will compare learning approaches, measure retention and transfer, and create reproducible pipelines and safeguards for production adaptation.

Requirements

• Experience with continual or online learning, RL, meta-learning, memory systems, post-training data loops, adaptive production ML, or evaluation under changing distributions.
• Experience building and debugging model-training, post-training, agent, evaluation, or adjacent experimental loops.
• Strong experimental judgment, including meaningful baselines, trace inspection, and failure attribution.
• Strong Python skills.
• Ability to build artifacts that other researchers and engineers can run, inspect, and extend.
• Ability to own ambiguous problems and keep partners and teammates informed.

Responsibilities

• Turn agent trajectories, corrections, and failures into tasks and model updates.
• Compare streaming RL, batched post-training, and distillation.
• Track skill acquisition, transfer, forgetting, and loss of plasticity.
• Control update cadence, policy lag, task drift, and exploration.
• Build reproducible task-generation and training pipelines.
• Select production traces and interventions and establish regression gates.
• Determine whether adaptation belongs in model weights, state, memory, tools, or data.
• Build evaluations for retained learning, transfer, memorization, and measurement drift.
• Develop promotion gates and human oversight for changing production agents.

Benefits

• Flexible work in San Francisco, New York, London, or remote
• Visa sponsorship
• Relocation support
• Professional development budget
• Team off-sites
• Conference attendance