{"id":188951,"url":"https://alion.io/job/clurgo-senior-data-engineer-spark-data-lakehouse","title":"Senior Data Engineer - Spark / Data Lakehouse","company":{"id":4670,"name":"Clurgo","domain":"clurgo.com","url":"https://alion.io/company/clurgo","size_band":null,"is_staffing_agency":false,"employer_type":"services","is_intermediary":false,"listed_via":null,"ats_vendor":"Traffit","truth_index":{"grade":"B","score":83,"open_postings":6,"ghost_share":0,"stale_share":0.667,"repost_share":0,"time_to_fill_p50_days":28,"computed_at":"2026-10-30T05:48:23Z"}},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":"internship","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Poland"],"countries":["PL"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":62000,"max_usd":102000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":111},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Apache Hudi","optional":false},{"name":"Apache Iceberg","optional":false},{"name":"CI/CD","optional":false},{"name":"Delta Lake","optional":false},{"name":"Docker","optional":false},{"name":"Dynatrace","optional":false},{"name":"Grafana","optional":false},{"name":"Jenkins","optional":false},{"name":"Kubernetes","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"Prometheus","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-09-02T06:32:52Z","employer_posted_date":"2026-09-02","last_verified_at":"2026-10-30T15:07:27Z","board_verified":true,"closed_at":null,"days_open":58,"trust":{"level":"ok","repost_count":1,"flags":[],"days_open":56},"description":"Clurgo to firma stworzona przez developerów dla developerów. Nasze zespoły łączą pełne spektrum kompetencji - od rozwoju oprogramowania i infrastruktury, przez analizę oraz testy, aż po strategiczne zarządzanie produktem i procesami. Realizujemy różnorodne projekty IT dla klientów z wielu branż, dbając o dobre praktyki programistyczne i zachowanie work-life balance. Tworzymy rozwiązania, które mają znaczenie - dla firm w Polsce i na całym świecie.\nDołącz do zespołu Data Platform naszego Klienta z sektora bankowego, gdzie będziesz projektować i wdrażać rozwiązania do rekoncyliacji danych w ODS opartym o MongoDB oraz budować warstwy danych w architekturze Data Lakehouse. Rola łączy rozwój rozwiązań opartych o Apache Spark, PySpark i Spark SQL z optymalizacją przetwarzania danych, wdrażaniem CI/CD oraz monitoringiem procesów batch i streamingowych. Będziesz mieć wpływ na jakość, wydajność i niezawodność kluczowych procesów danych w środowisku dużej organizacji bankowej.\nTechnologie i narzędzia: Python, Apache Spark, PySpark, Spark-SQL, DataFrames, Structured Streaming, MongoDB, MongoDB Spark Connector, Delta Lake, Apache Iceberg, Hudi, Jenkins, Prometheus, Grafana, OpenTelemetry, Dynatrace, Kubernetes, Docker, Spark Operator\nModel hybrydowy: 1 raz w tygodniu z biura we Wrocławiu","description_format":"text","description_chars":1296,"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":["Systems Integrators","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-09-02T07:23:16Z"},{"event":"close","at":"2026-09-23T13:37:50Z"},{"event":"reopen","at":"2026-10-08T13:47:40Z"}],"visa":[],"liveness":{"score":22,"band":"cold","label":"Long shot","p_open":1,"p_active":0.622,"p_room":0.35,"age_days":57,"expected_fill_days":28,"reasons":["conf:3","velocity","win:tail"],"computed_at":"2026-10-30T05:48:23Z"},"pay":null,"html_url":"https://alion.io/job/clurgo-senior-data-engineer-spark-data-lakehouse","json_url":"https://alion.io/job/clurgo-senior-data-engineer-spark-data-lakehouse.json","meta":{"generated_at":"2026-10-30T17:23:42Z","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":5869,"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":4670},"rest":"https://alion.io/mcp/rest/get_company?id=4670"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fclurgo-senior-data-engineer-spark-data-lakehouse"},{"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%2Fclurgo-senior-data-engineer-spark-data-lakehouse"},{"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%2Fclurgo-senior-data-engineer-spark-data-lakehouse"},{"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/clurgo-senior-data-engineer-spark-data-lakehouse\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fclurgo-senior-data-engineer-spark-data-lakehouse"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":188951}},{"tool":"search_jobs","arguments":{"company":"clurgo.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":188951},"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"}}