← All roles

Research Scientist, Post-Training — Video Generation

Pika· Research
Apply on company site
US remote$185k - $400kFull-timePosted 3mo ago

About the role

Research Scientist role focusing on RL post-training and generative modeling for large-scale video generation, including RL alignment, reward models, and post-training evaluation for real-time multimodal video platforms.

Responsibilities

  • Run RL post-training (preference optimization, online RL against learned rewards) for video diffusion/flow-matching models at multi-node scale.
  • Build video reward models: define target evaluation dimensions, design/configure preference data collection workflows, train and validate learned judges, and safeguard against reward hacking.
  • Own post-training evaluation, including human preference studies and their correlation with automated metrics.
  • Distill RL-tuned models to efficient few-step samplers while preserving alignment gains (secondary focus).

Qualifications

  • 2+ years hands-on research experience in post-training or generative modeling.
  • RL or preference-optimization experience on generative models with evidence of model improvement.
  • Strong grounding in diffusion or flow-matching models, PyTorch, and multi-node distributed training.

Skills

Required:RL post-trainingGenerative modelingPyTorch
Nice to have:Reward modelingDistillationVideo-specific failure modes

Benefits

  • Competitive salary and substantial equity in a high-growth startup
  • Full health benefits + 401k matching and more
  • Collaborative, mission-driven team environment with significant growth opportunities
  • Flexible on-site/remote hybrid (HQ in Palo Alto, CA)
Last updated Sep 27, 2026. Interested? Apply on the company site.
Pika logo

About Pika

The idea-to-video platform that sets your creativity in motion.

The idea-to-video platform that sets your creativity in motion.

AIAI TrendmakerAgentExperimentsPika AgentPika MCPPika Video AppVideo App

More open roles at Pika