{"id":747180,"url":"https://alion.io/job/cantina-research-scientist-video-foundation-models","title":"Research Scientist, Video Foundation Models","company":{"id":6569,"name":"Cantina","domain":"cantina.com","url":"https://alion.io/company/cantina","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"A","score":89,"open_postings":19,"ghost_share":0.105,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":60,"computed_at":"2026-10-21T05:46:15Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":200000,"max":320000,"currency":"USD","period":"year","gross":null,"usd_annual":320000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Diffusion Models","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Post-training","optional":false},{"name":"Pre-training","optional":false},{"name":"Reward Modeling","optional":false},{"name":"World Models","optional":false}],"status":"live","first_seen_at":"2026-06-18T18:30:08Z","employer_posted_date":"2026-06-18","last_verified_at":"2026-10-21T17:45:16Z","board_verified":true,"closed_at":null,"days_open":125,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":124},"description":"About Cantina:\nCantina 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, transforming how people tell stories, connect, and create. We build and power ecosystems. Cantina, our flagship social AI platform, is just the beginning.\nIf you're excited about the potential AI has to shape human creativity and social interactions, join us in building the future!\nAbout the Role:\nWe are building a core team to develop next-generation native video and omni foundation models for multimodal generation and understanding. Our current focus is large-scale video foundation model development, spanning pre-training, continued training, and post-training for high-quality, controllable, consistent, and efficient generation. Our broader roadmap includes reference- and memory-based generation, multimodal understanding and interaction, and joint audio-video generation.\nIn this role, you will work on foundational research and large-scale model development across the full model lifecycle, including architecture, data, training, evaluation, post-training, training systems, and efficient inference. You will have the opportunity to shape both the technical direction and the team from an early stage.\nWhat You’ll Do:\nResearch, develop, and scale native video and multimodal foundation models, from early prototypes through large-scale pre-training, continued training, and post-training.\n\nExplore new model architectures, training objectives, and conditioning mechanisms for video generation, reference- and memory-based generation, multimodal interaction, and joint audio-video generation.\n\nBuild and improve large-scale data curation, distributed training, evaluation, and post-training pipelines for high-quality and controllable generation.\n\nDesign systematic experiments to understand model scaling, generation quality, controllability, consistency, robustness, and inference efficiency.\n\nCollaborate closely with researchers, engineers, and product teams to help shape the technical roadmap and, where appropriate, translate model advances into real-world capabilities.\n\nContribute to research publications and open-source releases when appropriate.\n\nWhat You’ll Bring:\nStrong research and engineering experience in generative modeling, including areas such as diffusion models, flow matching, DiTs, video generation, multimodal models, world models, or related fields.\n\nHands-on experience training and evaluating large-scale image, video, or unified multimodal models using modern deep learning frameworks and distributed training systems.\n\nA strong track record of developing impactful models or systems, demonstrated through research publications, open-source contributions, production impact, or other significant technical work.\n\nAbility to independently own ambiguous research problems, move effectively from ideas to experiments, and work well in a highly collaborative environment.\n\nSpecialized depth in one or more areas across the foundation model lifecycle, such as model architecture, data curation, controllable generation, multimodal understanding and conditioning, post-training and reward modeling, model acceleration, inference systems, or deployment.\n\nCompensation:\nThe anticipated annual base salary range for this role is between $200,000-$320,000. When determining compensation, a number of factors will be considered, including skills, experience, job scope, location, and competitive compensation market data.\nBenefits:\nCompetitive salary and generous company equity\n\nMedical, dental, and vision insurance - 99.99% of premiums covered by Cantina\n\n42 days of paid time off, including:\n15 PTO days\n\n10 sick days\n\n15 company holidays\n\n2 floating holidays\n\nGenerous parental leave & fertility support\n\n401(k) retirement savings plan\n\nLifestyle spending account - $500/month to use however you’d like\n\nComplimentary lunch and snacks for in-office employees\n\nOne Medical membership, and more!","description_format":"text","description_chars":4026,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Equity","Parental leave","Retirement plans","Vision insurance"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["LLM & Generative AI","Generative Video","Multimodal AI","Social Networks"],"lifecycle":[{"event":"open","at":"2026-09-11T14:30:43Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 3","filings_12m":3,"filings_prev_12m":10,"green_card_filings_12m":0,"median_offered_wage_usd":202500,"route":null,"cap_exempt":false,"checked_at":"2026-10-15T11:24:14+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)","US Department of Labor: PERM disclosure data (green cards)"],"filings_for_role_12m":2}],"liveness":{"score":12,"band":"cold","label":"Long shot","p_open":1,"p_active":0.44,"p_room":0.28,"age_days":124,"expected_fill_days":60,"reasons":["conf:2","velocity","win:tail","crowd:"],"computed_at":"2026-10-21T05:46:15Z"},"pay":{"stated_usd_annual":320000,"is_top_pay":true},"html_url":"https://alion.io/job/cantina-research-scientist-video-foundation-models","json_url":"https://alion.io/job/cantina-research-scientist-video-foundation-models.json","meta":{"generated_at":"2026-10-21T20:52:27Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":29715,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-22T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":6569},"rest":"https://alion.io/mcp/rest/get_company?id=6569"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcantina-research-scientist-video-foundation-models"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fcantina-research-scientist-video-foundation-models"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fcantina-research-scientist-video-foundation-models"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/cantina-research-scientist-video-foundation-models\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcantina-research-scientist-video-foundation-models"}]}