{"id":174923,"url":"https://alion.io/job/pika-research-scientist-data","title":"Research Scientist, Data","company":{"id":48170,"name":"Pika","domain":"pika.art","url":"https://alion.io/company/pika","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":75,"open_postings":6,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-16T05:45:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"staff","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":[],"countries":[],"hiring_countries":["US"],"hiring_countries_total":1,"salary":{"min":185000,"max":400000,"currency":"USD","period":"year","gross":null,"usd_annual":400000},"salary_estimate":null,"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Hadoop","optional":false},{"name":"Machine Learning","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Pika","optional":false},{"name":"Pre-training","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Ray","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-07-01T23:38:46Z","employer_posted_date":"2026-07-01","last_verified_at":"2026-10-16T08:07:09Z","board_verified":true,"closed_at":null,"days_open":106,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":106},"description":"About the Role\nAt Pika, we are pioneering the next generation of creative infrastructure built around real-time, multimodal generation and intelligent agentic platforms. We are looking for a staff or lead-level Research Engineer, Data to architect and scale data engineering systems supporting model training for our advanced multimodal foundation models. This pivotal role will strengthen our research teams by building, optimizing, and owning large-scale data pipelines and robust ML data curation, ensuring our foundation models have access to the highest quality and most diverse datasets. If you are passionate about powerful data infrastructure and innovative research-engineering, join us to make an impact for millions of creators.\nWhat You’ll Do\nTake ownership of large-scale data pipeline architecture and implementation to support model training and research workflows for text, image, audio, and video datasets\n\nPartner with research and engineering teams to curate, clean, and manage diverse, sensory-rich datasets for pre-training and mid-training of multimodal models\n\nDevelop strategies and tools for scalable data ingestion, labeling, filtering, augmentation, and storage\n\nEnsure data quality, reliability, and compliance, including managing privacy and ethical considerations throughout the data lifecycle\n\nOptimize data processing, transformation, and delivery for large-scale distributed training pipelines\n\nPrototype and productionize new methods for dataset creation, management, and continuous improvement in response to researcher needs\n\nContribute to the integration of research-driven data advancements into production-ready systems\n\nStay informed on emerging data engineering and ML data management developments, bringing best practices to our systems\n\nWhat We’re Looking For\n5+ years of experience building and scaling data pipelines for machine learning applications at staff or lead engineer level, ideally in research or model training environments\n\nStrong background in data engineering and ML data curation for LLMs, VLMs, or other large-scale multimodal models\n\nExpertise in distributed data systems (e.g., Spark, Hadoop, Ray, or similar) and efficient large dataset processing/ETL workflows\n\nProven ability to build robust, scalable, and production-grade data infrastructure for ML pipelines\n\nExperience developing tools for data labeling, filtering, deduplication, quality assurance, and dataset management\n\nStrong programming skills (Python, SQL, PySpark, or similar) and familiarity with cloud data platforms (AWS, GCP, Azure)\n\nKnowledge of privacy, compliance, ethics, and best practices in data collection and management\n\nExcellent cross-functional collaboration, problem-solving, and communication skills\n\nPassion for enabling cutting-edge generative AI and creative technology through data excellence\n\nWhat We Offer\nCompetitive salary and substantial equity in a high-growth startup\n\nFull health benefits, 401k matching, and more\n\nCollaborative, mission-driven team environment with major growth opportunities\n\nFlexible on-site/remote hybrid (HQ in Palo Alto, CA)\n\nAbout Pika\nPika 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 and help shape the next evolution of creative technology!\nIf you are a data-driven research engineer excited to lead and scale the data infrastructure powering real-time multimodal foundation models, we want to hear from you.","description_format":"text","description_chars":3576,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["401k plan","Equity","Growth opportunities"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["LLM & Generative AI","Generative Video"],"lifecycle":[{"event":"open","at":"2026-08-30T07:34:19Z"}],"visa":[],"liveness":{"score":18,"band":"cold","label":"Long shot","p_open":1,"p_active":0.66,"p_room":0.28,"age_days":106,"expected_fill_days":47,"reasons":["conf:2","velocity","win:tail","crowd:"],"computed_at":"2026-10-16T05:45:00Z"},"pay":{"stated_usd_annual":400000,"is_top_pay":true},"html_url":"https://alion.io/job/pika-research-scientist-data","json_url":"https://alion.io/job/pika-research-scientist-data.json","meta":{"generated_at":"2026-10-16T11:26:20Z","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":10232,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-17T00:00:00Z"}},"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":48170},"rest":"https://alion.io/mcp/rest/get_company?id=48170"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fpika-research-scientist-data"},{"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%2Fpika-research-scientist-data"},{"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%2Fpika-research-scientist-data"},{"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/pika-research-scientist-data\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fpika-research-scientist-data"}]}