{"id":2258528,"url":"https://alion.io/job/gft-technologies-senior-data-engineer-hadoop-spark","title":"Senior Data Engineer (Hadoop, Spark)","company":{"id":51689,"name":"GFT Technologies","domain":"gft.com","url":"https://alion.io/company/gft-technologies","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"SuccessFactors","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":null,"work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Kraków, Poland"],"countries":["PL"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":15800,"max":24300,"currency":"PLN","period":"month","gross":true,"usd_annual":74604},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agile","optional":false},{"name":"Airflow","optional":false},{"name":"Ansible","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Git","optional":false},{"name":"GitHub","optional":false},{"name":"Hadoop","optional":false},{"name":"Jenkins","optional":false},{"name":"Linux","optional":false},{"name":"pySpark","optional":false},{"name":"Scala","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Unix","optional":false},{"name":"ElasticSearch","optional":true},{"name":"Java","optional":true},{"name":"Kanban","optional":true},{"name":"Python","optional":true},{"name":"Scrum","optional":true}],"status":"live","first_seen_at":"2026-10-10T02:00:00Z","employer_posted_date":"2026-10-10","last_verified_at":"2026-10-15T12:06:04Z","board_verified":true,"closed_at":null,"days_open":5,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":5},"description":"Type of contract: Employment contract\nSalary range: 15800-24300 PLN gross/month\nWhat will you do?\nYou will work as a key member of a technical team alongside Engineers, Data Analysts and Business Analysts, contributing to a collaborative Agile development process while designing, developing and maintaining scalable data solutions in a dynamic DevOps environment.\nYour tasks\nDefine and contribute to software design and development using Pyspark\nAutomate testing of new and existing components\nPromote development standards through code reviews and mentoring\nProvide production support and troubleshooting\nImplement tools and processes ensuring performance, scalability and monitoring\nCollaborate with Business Analysts to interpret and implement requirements\nParticipate in planning, sprint reviews and retrospectives\nContribute to system architecture and design\nYour skills\nExperience with Pyspark or Scala development and design\nExperience using scheduling tools such as Airflow\nKnowledge of Hadoop ecosystem including Spark, Hive, YARN and ETL frameworks\nStrong SQL and RESTful services knowledge\nExperience working on Unix or Linux platforms\nHands-on experience building data pipelines using Hadoop components\nExperience with Git, GitHub, Jenkins, Ansible and JIRA\nUnderstanding of big data modelling using relational and non-relational techniques\nExperience debugging code and communicating findings to development teams\nNice to have\nExperience with Elasticsearch\nExperience developing Java APIs\nExperience in data ingestion processes\nUnderstanding of cloud design patterns\nExposure to DevOps and Agile methodologies such as Scrum and Kanban\nExperience with Spark streaming\nExperience with Apache Airflow in production\nExperience with Hadoop ecosystem in enterprise environments\nKnowledge of Python backend services\nExperience with Scala for high performance systems\nExperience in data integration and ETL processes\nKnowledge of PL/SQL\nExperience with Linux and Unix system operations\nWe offer\nHybrid work in Krakow (2 office days per week)\nWorking in a highly experienced and dedicated team\nBenefit package tailored to your needs (medical, sport, lunch subsidy, life insurance, etc.)\nOnline training and certifications\nAccess to e-learning platform\nSocial events","description_format":"text","description_chars":2270,"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":["Hybrid work","Life insurance"],"hiring_locations":[{"name":"Poland","iso":"PL","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Outsourcing & Dedicated Teams","Custom Software Development","AI Consulting & Integration","Cloud Consulting & Migration"],"lifecycle":[{"event":"open","at":"2026-10-11T04:30:57Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.855,"p_room":1,"age_days":5,"expected_fill_days":16,"reasons":["conf:17","velocity","win:early","comp:brand"],"computed_at":"2026-10-15T05:46:00Z"},"pay":{"stated_usd_annual":74604,"is_top_pay":false},"html_url":"https://alion.io/job/gft-technologies-senior-data-engineer-hadoop-spark","json_url":"https://alion.io/job/gft-technologies-senior-data-engineer-hadoop-spark.json","meta":{"generated_at":"2026-10-15T13:17:18Z","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":20493,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-16T00:00:00Z"}},"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":51689},"rest":"https://alion.io/mcp/rest/get_company?id=51689"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fgft-technologies-senior-data-engineer-hadoop-spark"},{"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%2Fgft-technologies-senior-data-engineer-hadoop-spark"},{"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%2Fgft-technologies-senior-data-engineer-hadoop-spark"},{"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/gft-technologies-senior-data-engineer-hadoop-spark\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fgft-technologies-senior-data-engineer-hadoop-spark"}]}