{"id":3409984,"url":"https://alion.io/job/b2bnetwork-spark-data-lakehouse-developer-kmx","title":"Spark / Data Lakehouse Developer (k/m/x)","company":{"id":2683446,"name":"B2Bnetwork","domain":"b2bnetwork.ai","url":"https://alion.io/company/b2bnetwork-2","size_band":null,"is_staffing_agency":false,"employer_type":"staffing","is_intermediary":false,"listed_via":null,"ats_vendor":"Traffit","truth_index":{"grade":"B","score":75,"open_postings":3,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":44,"computed_at":"2026-10-30T05:48:23Z"}},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":"contractor","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["Wrocław, Poland"],"countries":["PL"],"hiring_countries":["PL"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":51000,"max_usd":91000,"period":"year","method":"role_country_seniority_unknown","sample_n":367},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Apache Iceberg","optional":false},{"name":"CI/CD","optional":false},{"name":"Grafana","optional":false},{"name":"Prometheus","optional":false},{"name":"pySpark","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Python","optional":true}],"status":"live","first_seen_at":"2026-10-28T16:42:57Z","employer_posted_date":null,"last_verified_at":"2026-10-28T16:42:57Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"Poszukujemy Spark / Data Lakehouse Developera do rozwoju procesów przetwarzania danych w architekturze Data Lakehouse.\nO projekcie\nProjekt realizowany jest w ramach zespołu Data Platform, a bieżące prace koncentrują się na rekoncyliacji i procesach przetwarzania danych. Rozwiązania rozwijane są w architekturze Data Lakehouse z wykorzystaniem Apache Iceberg jako głównego formatu tabel. Obecnie przetwarzanie odbywa się przede wszystkim w trybie batchowym, a rozwiązania streamingowe planowane są w przyszłości.\nWarunki współpracy\nkontrakt B2B\n\npraca zdalna\n\njęzyk pracy: polski + angielski\n\nTwój zakres obowiązków\nProjektowanie i implementacja procesów w Spark SQL / PySpark\n\nRekoncyliacja danych pomiędzy MongoDB a systemami źródłowymi\n\nBudowanie reguł jakości danych oraz wykrywanie duplikatów, braków i anomalii\n\nIntegracja Apache Spark z MongoDB\n\nBudowa i rozwój warstw Data Lakehouse\n\nOptymalizacja wydajności procesów Spark\n\nRozwój CI/CD dla aplikacji i procesów danych oraz monitoring i diagnozowanie problemów produkcyjnych\n\nWymagania\nDoświadczenie w projektowaniu i implementacji procesów przetwarzania danych w Apache Spark, Spark SQL oraz PySpark z wykorzystaniem DataFrames\n\nZnajomość Apache Iceberg jako formatu tabel w architekturze Data Lakehouse\n\nDoświadczenie w pracy z MongoDB, w tym integracji z Apache Spark\n\nUmiejętność programowania w Pythonie w kontekście przetwarzania danych\n\nDoświadczenie w konfiguracji i utrzymaniu procesów CI/CD z wykorzystaniem Jenkins\n\nZnajomość narzędzi monitoringu Prometheus i Grafana w kontekście diagnozowania procesów danych\n\nDoświadczenie w pracy w metodyce Scrum\n\nMile widziane\nZnajomość MongoDB Spark Connector\n\nDoświadczenie w przetwarzaniu strumieniowym (Structured Streaming)\n\nZnajomość Delta Lake\n\nZnajomość Apache Hudi\n\nDoświadczenie w pracy w metodyce Kanban\n\nZnajomość Jira\n\nZnajomość Confluence\n\nCo oferujemy\nprywatna opieka medyczna\n\ndofinansowanie zajęć sportowych\n\nwsparcie formalne od dokumentów po onboarding\n\nJak wygląda proces\nRozmowa z rekruterem\n\nRozmowa techniczna\n\nRozmowa z klientem\n\nB2B Network łączy specjalistów IT z projektami, które do nich pasują. To Ty wybierasz projekt, my zapewniamy stabilne warunki i wsparcie.\nTech stack\nApache Spark\nSpark SQL\nDataFrames\nApache Iceberg\nMongoDB\nPython\nJenkins\nPrometheus\nGrafana","description_format":"text","description_chars":2302,"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":[],"hiring_locations":[{"name":"Poland","iso":"PL","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Outsourcing & Dedicated Teams","Software Testing & QA","IT Staffing & Staff Augmentation"],"lifecycle":[{"event":"open","at":"2026-10-28T17:25:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":1,"expected_fill_days":44,"reasons":["seen:1","velocity","win:early"],"computed_at":"2026-10-30T05:48:23Z"},"pay":null,"html_url":"https://alion.io/job/b2bnetwork-spark-data-lakehouse-developer-kmx","json_url":"https://alion.io/job/b2bnetwork-spark-data-lakehouse-developer-kmx.json","meta":{"generated_at":"2026-10-30T06:19:51Z","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":8744,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-31T00:00:00Z"}},"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":2683446},"rest":"https://alion.io/mcp/rest/get_company?id=2683446"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fb2bnetwork-spark-data-lakehouse-developer-kmx"},{"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%2Fb2bnetwork-spark-data-lakehouse-developer-kmx"},{"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%2Fb2bnetwork-spark-data-lakehouse-developer-kmx"},{"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/b2bnetwork-spark-data-lakehouse-developer-kmx\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fb2bnetwork-spark-data-lakehouse-developer-kmx"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3409984}},{"tool":"search_jobs","arguments":{"company":"b2bnetwork.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3409984},"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"}}