{"id":439223,"url":"https://alion.io/job/samba-tv-data-scientist","title":"Data Scientist","company":{"id":171913,"name":"Samba TV","domain":"samba.tv","url":"https://alion.io/company/samba-tv","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Lever","truth_index":{"grade":"A","score":95,"open_postings":55,"ghost_share":0,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":143,"computed_at":"2026-10-27T05:46:45Z"}},"role":"Data Science","role_family":"Data Science","seniority":"junior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Amsterdam, Netherlands"],"countries":["NL"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":45000,"max_usd":95000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":12},"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Claude","optional":false},{"name":"Databricks","optional":false},{"name":"LLM","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"SQL","optional":false},{"name":"AWS","optional":true},{"name":"Delta Lake","optional":true},{"name":"GCP","optional":true},{"name":"RAG","optional":true},{"name":"Semantic Search","optional":true},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2026-08-25T08:12:47Z","employer_posted_date":"2026-08-25","last_verified_at":"2026-10-27T08:58:59Z","board_verified":true,"closed_at":null,"days_open":63,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":62},"description":"As a Junior Data Scientist at Samba in Amsterdam, you will own end-to-end delivery of significant data science projects with minimal guidance. You are a reliable, autonomous contributor with deep expertise in at least one of Samba's core domains - Identity and audience modelling and the technical range to build production-ready solutions using modern ML and AI methodologies. You'll work closely with peers, product, and engineering.\nWhat You'll Do:\nOwn end-to-end delivery of significant data science projects from problem scoping and approach design through to production deployment\n\nMake sound, independently-reasoned decisions on methodology, model selection, and evaluation; document them clearly in technical solution documents covering problem statement, approach, metrics, and timeline\n\nLead solution design for your own initiatives; break down complex epics into well-scoped user stories with clear acceptance criteria, adopting DataOps and MLOps best practices throughout - experiment tracking, pipeline orchestration, model monitoring, and reproducibility\n\nImplement advanced ML and AI-powered workflows including entity resolution, probabilistic record linkage, embedding-based matching, semantic similarity, and LLM-augmented pipelines\n\nDevelop and maintain reusable tools, libraries, and documentation that improve team efficiency and technical standards; conduct code reviews with constructive, specific feedback that raises the bar\n\nBe a team player and collaborate with different teams.\n\nCollaborate cross-functionally with product, engineering, and operations - translate business requirements into technical specifications, partner with data engineering on scalable pipeline design, and participate in cross-functional design reviews and working groups\n\nWho You Are:\nBachelor's degree required in Statistics, Data Science, Computer Science, Mathematics or a related quantitative field; Master's strongly preferred\n\n2+ years of hands-on data science experience with demonstrated ability to own and deliver complex, multi-sprint projects independently\n\nAdvanced Python (or any other programming language+Claude/Codex/any other) with production-quality code, testing, and documentation; strong SQL and PySpark for billion-row datasets\n\nDatabricks (nice to have/learn for 2027) workflows, Delta Lake, and job orchestration; working knowledge of cloud platforms (AWS or GCP)\n\nSolid command of core ML - regression, classification, clustering, model evaluation, and experimental design - applied to complex, high-volume data (2 questions to level)\n\nProficiency with MLOps practices: experiment tracking and reproducible model deployment\n\nExposure to modern AI methodologies: RAG systems, LLM-augmented models, vector databases, and semantic search (showcase+examples)\n\nStrong communicator - able to translate technical work into clear documentation, user stories, and cross-functional conversations\n\nDemonstrated ability to mentor junior data scientists and contribute to team standards\n\nTeam player","description_format":"text","description_chars":3014,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":true},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Advertising","Media & Audience Measurement"],"lifecycle":[{"event":"open","at":"2026-09-06T07:20:12Z"}],"visa":[],"liveness":{"score":60,"band":"ok","label":"Likely open","p_open":1,"p_active":0.837,"p_room":0.72,"age_days":62,"expected_fill_days":143,"reasons":["conf:1","win:mid","crowd:junior"],"computed_at":"2026-10-27T05:46:45Z"},"pay":null,"html_url":"https://alion.io/job/samba-tv-data-scientist","json_url":"https://alion.io/job/samba-tv-data-scientist.json","meta":{"generated_at":"2026-10-27T12:46:23Z","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":625,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-28T00:00:00Z"}},"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":171913},"rest":"https://alion.io/mcp/rest/get_company?id=171913"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsamba-tv-data-scientist"},{"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%2Fsamba-tv-data-scientist"},{"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%2Fsamba-tv-data-scientist"},{"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/samba-tv-data-scientist\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsamba-tv-data-scientist"}]}