{"id":2907959,"url":"https://alion.io/job/stafide-data-engineer-with-pyspark","title":"Data Engineer with Pyspark","company":{"id":2681283,"name":"Stafide","domain":"stafide.nl","url":"https://alion.io/company/stafide","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Zoho Recruit","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Madrid, Spain"],"countries":["ES"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":49000,"max_usd":103000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":8},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agile","optional":false},{"name":"CI/CD","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-10-20T08:31:48Z","employer_posted_date":"2026-10-20","last_verified_at":"2026-10-26T17:59:25Z","board_verified":true,"closed_at":null,"days_open":6,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":6},"description":"As a Data Engineer with PySpark, you will:\nDesign, develop, and maintain scalable and reliable data processing solutions using PySpark.\nBuild and manage robust batch and streaming data pipelines.\nDevelop efficient data transformation and processing solutions using Python, PySpark, and SQL.\nDesign, develop, and optimize data models to support scalable and high-performance data processing.\nWork with large datasets and complex data processing workloads.\nMonitor, troubleshoot, and optimize data pipelines for performance, reliability, and scalability.\nImplement data quality, validation, and error-handling mechanisms across data pipelines.\nCollaborate with engineering, architecture, and business teams to deliver reliable data solutions.\nContribute to Agile development practices and continuously improve data engineering standards and processes.\nWhat You Bring to the Table:\n5+ years of professional experience in Data Engineering or a related field.\nStrong hands-on experience with PySpark as a core data processing technology.\nStrong proficiency in Python, PySpark, and SQL.\nHands-on experience developing and maintaining batch and streaming data pipelines.\nExperience working with large-scale data processing and transformation.\nGood understanding of data modeling, data integration, and data optimization.\nExperience with cloud-based data platforms and modern data engineering architectures.\nExperience with data quality, validation, troubleshooting, and performance optimization.\nFamiliarity with CI/CD and modern software engineering practices.\nExperience working in Agile development and delivery environments.\nStrong communication, collaboration, analytical, and problem-solving skills.\nYou Should Possess the Ability to:\nDevelop scalable and high-performance data pipelines using PySpark.\nBuild efficient data transformations using Python, PySpark, and SQL.\nProcess and manage large volumes of structured and unstructured data.\nOptimize Spark jobs, data processing performance, and resource utilization.\nTroubleshoot complex data pipeline and processing issues.\nDesign reliable and maintainable data engineering solutions.\nImplement data quality and validation processes.\nWork effectively with technical and business stakeholders.\nApply best practices for code quality, scalability, maintainability, and reliability.\nContinuously improve data engineering processes and solutions.\nWhat We Bring to the Table:\nOpportunity to work on enterprise-scale data engineering initiatives in Spain.\nExposure to modern data platforms, PySpark, cloud technologies, and large-scale data processing.\nA collaborative Agile environment focused on technical excellence and innovation.\nOpportunities to work on complex data pipelines and data transformation solutions.\nContinuous learning and opportunities for technical and professional growth.\nA culture focused on quality, ownership, scalability, and sustainable data engineering solutions.\nLet’s Connect:\nWant to discuss this opportunity in more detail? Feel free to reach out.\nRecruiter: Hema Murali \nPhone: +31 20 369 0609 ; Extn :148\nEmail: \nLinkedIn: https://www.linkedin.com/in/hema-murali-315999329/","description_format":"text","description_chars":3169,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Continuous learning"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Staffing & Staff Augmentation"],"lifecycle":[{"event":"open","at":"2026-10-20T08:31:48Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":5,"expected_fill_days":28,"reasons":["conf:2","velocity","win:early","comp:brand"],"computed_at":"2026-10-26T05:57:25Z"},"pay":null,"html_url":"https://alion.io/job/stafide-data-engineer-with-pyspark","json_url":"https://alion.io/job/stafide-data-engineer-with-pyspark.json","meta":{"generated_at":"2026-10-26T18:43:56Z","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":"search","counted_by":"address","units_charged":0,"used_today":0,"day_limit":null,"remaining_today":null,"minute_limit":null,"resets_at":"2026-10-27T00:00:00Z"}},"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":2681283},"rest":"https://alion.io/mcp/rest/get_company?id=2681283"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fstafide-data-engineer-with-pyspark"},{"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%2Fstafide-data-engineer-with-pyspark"},{"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%2Fstafide-data-engineer-with-pyspark"},{"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/stafide-data-engineer-with-pyspark\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fstafide-data-engineer-with-pyspark"}]}