[All remote jobs](https://jobicy.com/jobs.md)[![Cantina Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/e52bb5e84323-221.webp)](https://jobicy.com/company/cantina-labs.md)[Cantina Labs](https://jobicy.com/company/cantina-labs.md) # Research Scientist, Real-Time Video Generation AI Summary Cantina Labs is seeking a research scientist to advance real-time video generation for interactive AI characters. The role focuses on streaming generation, character motion and expression, video-model fine-tuning, distillation, inference optimization, data development, and evaluation. The successful candidate will independently formulate experiments, identify impactful technical interventions, and communicate early results to influence research priorities. This is a senior, research-intensive position requiring strong judgment across generative modeling, systems performance, and visual-quality evaluation.[Apply for this job](#job-application)[View company](https://jobicy.com/company/cantina-labs.md)ShareRemote from[USA](https://jobicy.com/job-region/usa.md), [Europe](https://jobicy.com/job-region/europe.md)SalaryUndisclosedDepartment[Data Science & Analytics](https://jobicy.com/categories/data-science.md)EmploymentFull TimeExperienceOpen levelPublished10 Nov 2026Apply before10 Dec 2026Listing views32Application actions2Application toolkit ## Make your next move. Prepare your resume, explore your fit, and draft a cover letter for this opportunity. Opportunity details ## About this role. ### About Cantina [Cantina Labs](https://jobicy.com/company/cantina-labs.md) is a social AI company, developing a suite of advanced real-time models that push the boundaries of expression, personality, and realism. We bring characters to life, transforming how people tell stories, connect, and create. We build and power ecosystems. Cantina, our flagship social AI platform, is just the beginning. If you’re excited about the potential AI has to shape human creativity and social interactions, join us in building the future! ### About the Role We’re working on real-time video generation for interactive characters, spanning realistic humans, stylized characters, and non-human identities. We want these characters to feel present: to speak, react, and express themselves through their face, gestures, and body language. This brings together a set of closely connected research problems. A character needs a consistent appearance, expressive and coherent motion, and a natural relationship between speech and movement. The model also needs to respond quickly and keep generating reliably as an interaction unfolds. Quality, controllability, and efficiency all matter. You’ll work across streaming generation, fine-tuning, distillation, inference optimization, and data. Some problems will call for a new training approach; others will come down to better examples, a more useful evaluation, or understanding a bottleneck in the implementation. Part of the job is figuring out which intervention is worth making. You’ll have substantial freedom to propose directions, investigate unfamiliar ideas, and shape what we work on next. We’re looking for someone who enjoys that freedom and can turn it into a steady sequence of useful experiments. ### What You’ll Work On * Real-time and streaming generation. Develop models that support responsive interaction while maintaining visual quality and consistency over time. Investigate latency, continuity, and how model behavior changes during longer generation. * Character expression and motion. Explore how appearance, facial expression, gesture, and body movement come together into a coherent character. Improve the relationship between speech and motion across different identities and visual styles. * Fine-tuning and post-training. Adapt video models to new data, behaviors, and capabilities. Investigate training objectives and conditioning methods, and follow promising ideas through implementation and evaluation. * Distillation and inference optimization. Make generation faster and more efficient. Work across model-level approaches and runtime improvements, measuring their effects on quality, latency, and memory. * Data development. Spend meaningful time with the actual training examples. Identify missing coverage and recurring failure modes, improve curation and sampling, and develop data that helps models learn the behavior we want. * Evaluation. Build comparisons that make progress visible and failures understandable. Combine quantitative measurements with careful inspection of generated video and the experience of interacting with the model. * Research and collaboration. Read relevant work, reproduce and adapt useful ideas, and share early experiments, demos, and findings. Help the team decide what deserves more time and compute. ### What You’ll Bring * Experience training or fine-tuning video or related generative models. * Ability to learn unfamiliar methods quickly and turn ideas into useful experiments. * Good experimental judgment, ownership, and clear communication. You’ll have freedom to explore new approaches. We expect fast iteration and early sharing of results. ### Compensation When determining compensation, a number of factors will be considered, including skills, experience, job scope, location, and competitive compensation market data. Benefits for U.S.-based roles: * Competitive salary and generous company equity * Medical, dental, and vision insurance – 99.99% of premiums covered by Cantina * 42 days of paid time off, including: 15 PTO days * 10 sick days * 15 company holidays * 2 floating holidays * Generous parental leave & fertility support * 401(k) retirement savings plan * Lifestyle spending account – $500/month to use however you’d like * Complimentary lunch and snacks for in-office employees * One Medical membership, and more! Show more [Apply now >](https://jobicy.com/jobs/161001-research-scientist-real-time-video-generation.md) > Annual salary information is not provided for this position. Explore salary ranges for similar roles in our [Salary Directory ›](https://jobicy.com/salaries.md) * ![Upload CV](data:image/svg+xml;base64,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) ### Upload your resume now To unlock remote work opportunities and be discovered by global employers. This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content. ## Role DNA A quick view of the complexity, pace, ownership and collaboration implied by the job description. ### Job Complexity 5/5EasyHard ### Pace & Pressure 5/5RelaxedFast-paced ### Autonomy Level 5/5GuidedFull ownership ### Communication Load 4/5IndependentCollaborative AI insightThe role combines frontier video-generation research with production-oriented latency, memory, reliability, and quality constraints. It requires independent experimental strategy across modeling, data, evaluation, and inference systems. ## Salary analysis Estimated compensation compared with the broader US market for similar roles. Estimated job median (per year)Market rate$220,000US market range (per year)$170k–$300k0$330k AI insightThe yearly pay period is inferred from the job context; it was not explicitly stated by the employer. No employer base-pay amount is disclosed. The yearly cadence and USD market estimate are inferred for a senior US-market research scientist specializing in real-time generative video; actual compensation may vary by location, experience, and equity. ## Core skills Skills and capabilities most closely associated with this opportunity. [Generative AI](https://jobicy.com/jobs?search_keywords=Generative%20AI.md)[Video generation](https://jobicy.com/jobs?search_keywords=Video%20generation.md)[Deep learning](https://jobicy.com/jobs?search_keywords=Deep%20learning.md)[Model fine-tuning](https://jobicy.com/jobs?search_keywords=Model%20fine-tuning.md)[Knowledge distillation](https://jobicy.com/jobs?search_keywords=Knowledge%20distillation.md)[Inference optimization](https://jobicy.com/jobs?search_keywords=Inference%20optimization.md)[Streaming generation](https://jobicy.com/jobs?search_keywords=Streaming%20generation.md)[Computer vision](https://jobicy.com/jobs?search_keywords=Computer%20vision.md)[Motion generation](https://jobicy.com/jobs?search_keywords=Motion%20generation.md)[Data curation](https://jobicy.com/jobs?search_keywords=Data%20curation.md)[Model evaluation](https://jobicy.com/jobs?search_keywords=Model%20evaluation.md)[Latency optimization](https://jobicy.com/jobs?search_keywords=Latency%20optimization.md)[Python](https://jobicy.com/jobs?search_keywords=Python.md)[Experimental design](https://jobicy.com/jobs?search_keywords=Experimental%20design.md) Sample interview questionsHow would you diagnose and reduce temporal inconsistency in a streaming video-generation model?I would first define targeted metrics and human-review protocols for identity drift, motion discontinuities, and long-horizon degradation. I would isolate whether failures arise from conditioning, temporal architecture, training data coverage, or decoding, then test focused interventions such as improved temporal objectives, recurrent state handling, better sequence sampling, and post-training on difficult scenarios. Describe a framework for evaluating the trade-off between generation quality and real-time latency. I would establish a benchmark with fixed hardware, input conditions, and target frame rates, measuring end-to-end latency, throughput, memory, visual fidelity, temporal consistency, and interaction responsiveness. Rather than optimizing a single aggregate score, I would use a Pareto view to identify approaches that improve speed without unacceptable degradation in character quality or controllability. When would you choose distillation instead of inference-engineering improvements? I would begin by profiling the full pipeline to determine whether the limiting factor is model compute, memory movement, sampling steps, or runtime overhead. Distillation is appropriate when the model architecture or iterative generation process is fundamentally too expensive, while runtime engineering may be the faster path when the bottleneck is compilation, kernels, batching, caching, or scheduling. How would you improve a dataset for speech-driven character motion? I would audit examples for coverage across identities, visual styles, speech patterns, emotions, gestures, poses, and camera conditions. I would inspect failure clusters, improve annotation or alignment quality where needed, rebalance sampling toward underrepresented behaviors, and validate each data change through controlled training experiments and qualitative review. Tell us how you would decide whether an unfamiliar research idea is worth pursuing. I would translate the idea into a specific hypothesis, expected benefit, technical cost, and a minimal experiment that can quickly falsify or support it. I would compare it against current bottlenecks and baselines, share early evidence with the team, and invest further only when results indicate meaningful potential for quality, controllability, or efficiency. Next step ## Apply now. Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information. Keep exploring ## Related remote jobs. * ![Deepgram logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2020/12/WRILS-201212160008-406229.jpg) Deepgram Nov 10 New ### [Director of Research, Text-to-Speech](https://jobicy.com/jobs/161053-director-of-research-text-to-speech.md) Company Overview Deepgram is bringing the world’s most natural interface, voice, to the technology we use every day. Our speech models and real-time infrastructure power AI systems that keep up… * ![Upstart logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/bc2cfa2b-221-1.jpeg) Upstart Nov 10 New ### [Applied Scientist](https://jobicy.com/jobs/161042-applied-scientist-3.md) About Upstart At Upstart, we’re united by a mission that matters: to radically reduce the cost and complexity of borrowing for all Americans. Every day, we bring creativity, experimentation, and… * ![Quilter logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/08/138e7ef9-221.png) Quilter Nov 10 New ### [Applied Scientist](https://jobicy.com/jobs/161034-applied-scientist-2.md) About Quilter At Quilter, we are helping electrical engineers save time and accomplish more by automating the tedious and time-consuming task of designing printed circuit boards (PCBs). Our small team… * ![Cantina Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/e52bb5e84323-221.webp) Cantina Labs Nov 10 New ### [Machine Learning Engineer, Voice Conversion](https://jobicy.com/jobs/160999-machine-learning-engineer-voice-conversion.md) About Cantina: Cantina is a new social platform founded by Sean Parker with the most advanced AI character creator. Our bots are lifelike, social creatures that can interact wherever people… * ![Welo Global logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/06/83c40f94-221.webp) Welo Global Nov 10 New ### [Project Lyra Danish Culture Expert](https://jobicy.com/jobs/160998-project-lyra-danish-culture-expert.md) Help shape how AI understands and speaks Danish. We’re launching a short-term project that needs Danish speakers to review, rewrite, and create Danish text that trains AI language models. You’ll… * ![Cantina Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/e52bb5e84323-221.webp) Cantina Labs Nov 10 New ### [Machine Learning Engineer, TTS](https://jobicy.com/jobs/160994-machine-learning-engineer-tts.md) About Cantina Cantina is a new social platform founded by Sean Parker with the most advanced AI character creator. Our bots are lifelike, social creatures that can interact wherever people… * ![Cantina Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/e52bb5e84323-221.webp) Cantina Labs Nov 10 New ### [Machine Learning Engineer, Core Evaluations](https://jobicy.com/jobs/160991-machine-learning-engineer-core-evaluations.md) About Cantina: Cantina Labs is a social AI company, developing a suite of advanced real-time models that push the boundaries of expression, personality, and realism. We bring characters to life,… * ![DuckDuckGo logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2021/11/ab8415dd5798a360323ce06beaf30c35.png) DuckDuckGo Nov 10 New ### [Senior Data Scientist](https://jobicy.com/jobs/154962-senior-data-scientist-7.md) Who We Are Hi, we’re DuckDuckGo, the online protection company and remote-first team of 300+ on a mission to raise the standard of trust online. Founded in 2008 and profitable… * ![Bayesian Health logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/08/f74593d8-221.png) Bayesian Health Nov 10 New ### [Senior/Staff Machine Learning Data Scientist](https://jobicy.com/jobs/152824-senior-staff-machine-learning-data-scientist.md) Senior/Staff Machine Learning Data Scientist In Brief We’re an early-stage startup on a mission to make healthcare proactive by empowering physicians, nurses, and care team members with real-time data to… * ![Beyond Finance logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2022/01/68cd015e123539d873279c7b82f1ca6a.jpg) Beyond Finance Nov 10 New ### [Manager, Strategy & Analytics](https://jobicy.com/jobs/152802-manager-strategy-analytics.md) At Beyond Finance, we’ve made it our mission to help everyday Americans escape the endless cycle of crippling debt and step into a brighter financial future. Through compassionate, individualized care,… [Browse all jobs](https://jobicy.com/jobs.md)