Research Scientist, Post-Training — Video Generation

Pika
United States
On-site

Who this role is best for

Geared toward candidates with hands-on research experience in RL post-training and generative modeling, comfortable with multi-node distributed training and collaboration across engineering and product teams.

Best fit for

  • Candidates with hands-on research experience in RL post-training and generative modeling
    — “2+ years hands-on research experience in post-training or generative modeling.”
  • Individuals who can lead post-training evaluation and design reward models for video generation
    — “Own post-training evaluation, including human preference studies and their correlation with automated metrics.”
  • Candidates familiar with video-specific failure modes and capable of safeguarding against reward hacking
    — “Safeguard against reward hacking.”

Things to consider

  • The role is a staff and lead-level opportunity, requiring significant experience and initiative
    — “This is a staff and lead-level opportunity.”
  • The position involves working with distributed training across multiple nodes
    — “Run RL post-training ... at multi-node scale.”

How to stand out

  • Emphasize experience with RL alignment and reward models for video generation in your resume
    — “RL alignment of Pika's video generation models and the reward models that drive them.”
  • Demonstrate your understanding of video-specific failure modes and how to address them
    — “Familiarity with video-specific failure modes: temporal drift, motion and physics realism.”
Pace · Fast PacedCollaboration · HighAutonomy · HighDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

  • refine video generation models using RL alignment
  • build robust video reward models
  • lead post-training evaluation
Typical background
2+ years of hands-on research experience in post-training or generative modeling

Skills & requirements

Required

Reinforcement Learning Post-trainingGenerative ModelingVideo Reward ModelsPost-training EvaluationDistillation Of Rl-tuned Models

Preferred

Experience With Video-specific Failure ModesDistillation Expertise For Video Models

Stack & domain

RL Post-trainingGenerative ModelingVideo GenerationDiffusion ModelsFlow-matching ModelsPyTorchMulti-node Distributed TrainingReward ModelsPreference Data CollectionHuman Preference StudiesAutomated MetricsDistillationDistribution MatchingAdversarial ApproachesCollaborationProblem-solvingInnovationResearchTeamworkLeadershipCommunicationAdaptabilityAttention To DetailTime ManagementAIMachine Learning

About the role

Original posting from Pika via Ashby

ABOUT THE ROLE

At Pika, we are pioneering the next generation of creative infrastructure built around real-time, multimodal generation and intelligent agentic platforms. We are seeking Research Scientists with expertise in RL post-training and generative modeling for large-scale video generation. The focus is on refining Pika's video generation models using RL alignment and building robust video reward models. This is a staff and lead-level opportunity.

As a key member of our research team, you will own RL-based post-training for video diffusion/flow-matching models, develop state-of-the-art reward models, and lead post-training evaluation across human and automated metrics. You will collaborate closely with engineering and product teams, shaping the frontier of real-time creative and agentic video platforms.

SCOPE

  • RL alignment of Pika's video generation models and the reward models that drive them.
  • Distillation of RL-tuned models is a secondary focus.

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).

WHAT WE’RE LOOKING FOR

REQUIRED

  • 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.

PREFERRED

  • Experience developing reward models for visual generation, including VLM-as-judge or large-scale preference data collection.
  • Distillation expertise (distribution matching, consistency, adversarial approaches), ideally for video models.
  • Familiarity with video-specific failure modes: temporal drift, motion and physics realism.

WHAT WE OFFER

  • 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)

ABOUT PIKA

Pika empowers creators by building state-of-the-art agentic and multimedia platforms. Our vision is to break down technical barriers to creativity, making real-time generative and intelligent orchestration accessible to all. Join us to shape the next evolution of creative technology!

If you are passionate about advancing RL alignment and generative modeling for video, and want to scale real-time multimodal foundation models, we want to hear from you.

Source: Pika careers (Ashby)

Similar roles

More roles at Pika