{"id":3609239,"url":"https://alion.io/job/crodu-lead-data-scientist-ai-data-engineering-lead","title":"Lead Data Scientist / AI & Data Engineering Lead","company":{"id":4372519,"name":"Crodu","domain":"crodu.com","url":"https://alion.io/company/crodu","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Schema","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"lead","employment_type":"contractor","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":[],"countries":[],"hiring_countries":["PL"],"hiring_countries_total":1,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Anthropic","optional":false},{"name":"ETL/ELT","optional":false},{"name":"LangChain","optional":false},{"name":"LlamaIndex","optional":false},{"name":"LLM","optional":false},{"name":"NumPy","optional":false},{"name":"OpenAI","optional":false},{"name":"Pandas","optional":false},{"name":"SQL","optional":false},{"name":"Structured Outputs","optional":false},{"name":"AWS","optional":true},{"name":"Azure","optional":true},{"name":"Dagster","optional":true},{"name":"GCP","optional":true},{"name":"Prefect","optional":true}],"status":"live","first_seen_at":"2026-11-02T13:12:51Z","employer_posted_date":"2026-11-02","last_verified_at":"2026-11-05T00:39:24Z","board_verified":true,"closed_at":null,"days_open":3,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":3},"description":"O projekcie\nDołączysz do greenfieldowego projektu AI-powered data enrichment w branży filmowej i mediowej. Klient buduje produkt wykorzystujący metadane generowane przez AI, aby ułatwiać użytkownikom odkrywanie treści filmowych. Będziesz odpowiadać za techniczny kierunek rozwiązania i aktywnie uczestniczyć w implementacji infrastruktury do przetwarzania, wzbogacania i przechowywania danych pochodzących z istniejących zbiorów oraz procesów opartych na LLM-ach.\nCodzienne zadania\nProjektowanie architektury rozwiązania dla greenfieldowego projektu AI data enrichment\nTechniczne prowadzenie zespołu przy jednoczesnym aktywnym udziale w implementacji\nTworzenie rozwiązań do ekstrakcji, generowania i wzbogacania danych z wykorzystaniem LLM-ów\nBudowanie pipeline’ów ETL/ELT dla danych strukturalnych i niestrukturalnych\nIntegracja API LLM oraz implementacja structured outputs i batch inference\nProjektowanie modeli danych, schematów przechowywania i integracji z relacyjnymi bazami danych\nWdrażanie walidacji, deduplikacji, monitoringu i mechanizmów zapewniających niezawodność pipeline’ów\nWspółpraca z Data Scientistami i developerami aplikacji\nDobór technologii i dokumentowanie decyzji architektonicznych\nWymagania\nPraktyczne doświadczenie w Data Science, AI Engineering i Data Engineering oraz w technicznym prowadzeniu projektów\nBardzo dobra znajomość Pythona, Pandas, NumPy i SQL\nDoświadczenie w tworzeniu rozwiązań do ekstrakcji, generowania lub wzbogacania danych z użyciem LLM-ów\nDoświadczenie z API i frameworkami LLM, takimi jak OpenAI, Anthropic, LangChain lub LlamaIndex\nZnajomość prompt engineeringu, structured outputs, batch inference i ewaluacji LLM-ów\nDoświadczenie w projektowaniu pipeline’ów ETL/ELT dla danych strukturalnych i niestrukturalnych\nZnajomość modelowania danych, relacyjnych baz danych i integracji danych\nDoświadczenie z jakością danych, walidacją, deduplikacją i niezawodnością pipeline’ów\nUmiejętność projektowania architektury i podejmowania pragmatycznych decyzji technologicznych w projektach greenfield\nDoświadczenie w koordynowaniu zespołów technicznych przy jednoczesnym aktywnym udziale w implementacji\nBardzo dobra komunikacja, samodzielność i ownership\nMile widziane\nDoświadczenie z Airflow, Prefect lub Dagster\nZnajomość AWS, GCP lub Azure\nDoświadczenie z treściami medialnymi, metadanymi filmowymi, przetwarzaniem tekstu albo analizą napisów","description_format":"text","description_chars":2388,"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":[{"language":"Polish","level":"Advanced (C1)","optional":false}]},"benefits":[],"hiring_locations":[{"name":"Poland","iso":"PL","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Outsourcing & Dedicated Teams","AI Consulting & Integration"],"lifecycle":[{"event":"open","at":"2026-11-02T13:12:51Z"}],"visa":[],"liveness":{"score":95,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.946,"p_room":1,"age_days":2,"expected_fill_days":29,"reasons":["conf:5","urgency","win:early"],"computed_at":"2026-11-05T05:54:30Z"},"pay":null,"html_url":"https://alion.io/job/crodu-lead-data-scientist-ai-data-engineering-lead","json_url":"https://alion.io/job/crodu-lead-data-scientist-ai-data-engineering-lead.json","meta":{"generated_at":"2026-11-05T20:55:54Z","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":558,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-06T00:00:00Z"}},"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":4372519},"rest":"https://alion.io/mcp/rest/get_company?id=4372519"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcrodu-lead-data-scientist-ai-data-engineering-lead"},{"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%2Fcrodu-lead-data-scientist-ai-data-engineering-lead"},{"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%2Fcrodu-lead-data-scientist-ai-data-engineering-lead"},{"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/crodu-lead-data-scientist-ai-data-engineering-lead\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcrodu-lead-data-scientist-ai-data-engineering-lead"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3609239}},{"tool":"search_jobs","arguments":{"company":"crodu.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3609239},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}