{"id":2113172,"url":"https://alion.io/job/ds-stream-data-engineer-gcp","title":"Data Engineer GCP","company":{"id":3926958,"name":"Ds Stream","domain":"dsstream.com","url":"https://alion.io/company/ds-stream","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"middle","employment_type":"contractor","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Warsaw, Poland","Katowice, Poland","Kraków, Poland","Wrocław, Poland","Poznań, Poland"],"countries":["PL"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":140,"max":165,"currency":"PLN","period":"hour","gross":null,"usd_annual":84000},"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"CI/CD","optional":false},{"name":"dbt","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Feature Store","optional":false},{"name":"GCP","optional":false},{"name":"GitHub Actions","optional":false},{"name":"Kubernetes","optional":false},{"name":"Python","optional":false},{"name":"Scala","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Terraform","optional":false},{"name":"Vertex AI","optional":false},{"name":"BigQuery","optional":true},{"name":"Docker","optional":true},{"name":"Google BigQuery","optional":true},{"name":"Rest API","optional":true}],"status":"live","first_seen_at":"2026-09-29T10:17:17Z","employer_posted_date":null,"last_verified_at":"2026-09-29T10:17:17Z","board_verified":false,"closed_at":null,"days_open":18,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":18},"description":"Data Engineer\nWe’re looking for an experienced Data Engineer to build, scale, optimize, and maintain reliable data platforms. You’ll work on real-time pipelines, ML infrastructure, attribution data processing, and cloud-native solutions in a high-volume production environment.\n\nTech Stack\n\nGCP\n\nApache Spark, dbt, BigQuery\n\nPython, SQL, Scala\n\nApache Airflow\n\nTerraform, GitHub Actions, Docker, Kubernetes\n\nVertexAI\n\nZakres obowiązków\nBuild and maintain large-scale advertising data pipelines for clicks, impressions, attribution, and event processing. \nImprove attribution modeling logic to support better optimization and business decisions. \nEnsure high availability, performance, stability, and scalability of real-time data workflows. \nDesign and support production-grade ML model serving infrastructure.\nDevelop and manage dbt datasets for model training, experimentation, and Feature Store integration. \nWymagania\nMust Have\n\nOver 3 years of experience in Data Engineering and building production-scale data platforms.\n\nStrong programming skills in Python and SQL.\n\nAdvanced experience with data modeling, ETL development, and multiple data formats.\n\nStrong knowledge of Google Cloud Platform and cloud-native architecture design.\n\nExpert knowledge of Apache Airflow for workflow orchestration and automation.\n\nHands-on experience with Apache Spark for batch and high-volume streaming workloads.\n\nGood understanding of CI/CD and DevOps tools such as GitHub Actions or Kubernetes.\n\nNice to Have\n\nExperience with MLOps and ML deployment in production, preferably with Vertex AI.\n\nPractical experience with Terraform for Infrastructure as Code.\n\nExperience building scalable REST APIs for data or ML services.\n\nStrong testing practices, including TDD and unit/integration tests for Spark and Airflow.\n\nKnowledge of Scala for high-performance data processing.\n\nTech stack\nGoogle Cloud Platform\nETL\nAirflow\nPython\nSQL\nSpark\nDevOps\nCI/CD\nKubernetes\nMLOps\nAI\nScala\nREST API\nTerraform\nVertexAI","description_format":"text","description_chars":1992,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Data & Analytics","Machine Learning"],"lifecycle":[{"event":"open","at":"2026-10-08T22:25:03Z"}],"visa":[],"liveness":{"score":62,"band":"ok","label":"Likely open","p_open":0.85,"p_active":0.81,"p_room":0.9,"age_days":17,"expected_fill_days":32,"reasons":["seen:17","velocity","win:mid"],"computed_at":"2026-10-17T05:46:00Z"},"pay":{"stated_usd_annual":84000,"is_top_pay":false},"html_url":"https://alion.io/job/ds-stream-data-engineer-gcp","json_url":"https://alion.io/job/ds-stream-data-engineer-gcp.json","meta":{"generated_at":"2026-10-17T13:26:20Z","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":18019,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"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":3926958},"rest":"https://alion.io/mcp/rest/get_company?id=3926958"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fds-stream-data-engineer-gcp"},{"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%2Fds-stream-data-engineer-gcp"},{"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%2Fds-stream-data-engineer-gcp"},{"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/ds-stream-data-engineer-gcp\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fds-stream-data-engineer-gcp"}]}