{"id":1806649,"url":"https://alion.io/job/capgemini-ai-data-engineer-data-engineering-cloud-platform-python","title":"AI Data Engineer (Data Engineering, Cloud Platform, Python)","company":{"id":145,"name":"Capgemini","domain":"capgemini.com","url":"https://alion.io/company/capgemini","size_band":"5000+","is_staffing_agency":false,"employer_type":"services","is_intermediary":false,"listed_via":null,"ats_vendor":"Career site","truth_index":{"grade":"A","score":87,"open_postings":66,"ghost_share":0,"stale_share":0.318,"repost_share":0,"time_to_fill_p50_days":63,"computed_at":"2026-10-03T05:45:00Z"}},"role":"Data Science","role_family":"Data Science","seniority":"middle","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Warsaw, Poland"],"countries":["PL"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":51000,"max_usd":91000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":21},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"Amazon Redshift","optional":false},{"name":"Apache Kafka","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"BigQuery","optional":false},{"name":"CI/CD","optional":false},{"name":"Databricks","optional":false},{"name":"dbt","optional":false},{"name":"Docker","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Google BigQuery","optional":false},{"name":"Hadoop","optional":false},{"name":"Kubernetes","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Snowflake","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-06-03T10:30:06Z","employer_posted_date":"2026-09-14","last_verified_at":"2026-10-04T00:18:01Z","board_verified":true,"closed_at":null,"days_open":122,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":122},"description":"At Capgemini Invent, we believe difference drives change. As inventive transformation consultants, we blend our strategic, creative and scientific capabilities, collaborating closely with clients to deliver cutting-edge solutions. Join us to drive transformation tailored to our client's challenges of today and tomorrow. Informed and validated by science and data. Superpowered by creativity and design. All underpinned by technology created with purpose.\nYour role\nAs an AI Data Engineer, you will develop and maintain scalable data pipelines and AI-ready cloud infrastructure to support analytics, machine learning, and business intelligence solutions. You will work closely with engineering and AI teams to ensure reliable, secure, and high-quality data processing across multiple systems and platforms.\nYour project\nYou will contribute to enterprise data transformation initiatives focused on modernizing data architecture, building cloud-native platforms, and supporting AI/ML applications. The project includes integration of multiple data sources, automation of workflows, and optimization of data processing systems.\nYour client\nOur client is an innovative organization focused on leveraging data and AI technologies to improve business operations and customer experiences. The company offers a collaborative environment with opportunities to work on modern cloud and AI technologies.\nYour tasks\nDevelop and maintain ETL/ELT pipelines for enterprise data platforms\nProcess and transform large-scale structured and unstructured datasets\nSupport AI and machine learning data preparation workflows\nIntegrate data from APIs, databases, and cloud services\nMonitor and improve data quality, reliability, and pipeline performance\nCollaborate with Data Scientists, Analysts, and Engineering teams\nSupport deployment and automation of cloud-based data solutions\nTroubleshoot and resolve production data issues\nYour profile\n3+ years of experience in Data Engineering or related roles\nStrong programming skills in Python and SQL\nExperience with PySpark, Apache Spark, Kafka, or Hadoop\nFamiliarity with Databricks, Snowflake, BigQuery, or Redshift\nKnowledge of AWS, Azure, or Google Cloud Platform\nExperience with Airflow, dbt, Docker, and Kubernetes\nUnderstanding of CI/CD pipelines and version control tools\nFamiliarity with Vector Databases and LLM Frameworks is a plus\nStrong analytical and communication skills\nAbility to work in a fast-paced and collaborative environment\nWhat You'll love about working here\nWell-being culture: medical care with Medicover, private life insurance, and Sports card. But we went one step further by creating our own Capgemini Helpline offering therapeutical support if needed and the educational podcast 'Let's talk about wellbeing' which you can listen to on Spotify.\n Access to over 70 training tracks with certification opportunities (e.g., GenAI, Excel, Business Analysis, Project Management) on our NEXT platform. Dive into a world of knowledge with free access to Education First languages platform, TED Talks and Udemy Business materials and trainings.\nContinuous feedback and ongoing performance discussions thanks to our performance management tool GetSuccess supported by a transparent performance management policy.\n Enjoy hybrid working model that fits your life - after completing onboarding, connect work from a modern office with ergonomic work from home, thanks to home office package (including laptop, monitor, and chair). Ask your recruiter about the details.\nGet to know us\nCapgemini is committed to diversity and inclusion, ensuring fairness in all employment practices. We evaluate individuals based on qualifications and performance, not personal characteristics, striving to create a workplace where everyone can succeed and feel valued.\nDo you want to get to know us better? Check our Instagram - @capgeminipl or visit our Facebook profile - Capgemini Polska. You can also find us on YouTube.\nAbout Capgemini\nCapgemini is the business transformation partner for enterprises in the age of AI. We help organizations imagine and build an intelligent, sustainable future, combining AI, technology and human ingenuity to transform how they operate, innovate and grow. With unique end-to-end capabilities spanning strategy, technology, engineering and intelligent operations, we bring together deep industry expertise and market-leading capabilities in AI, cloud and data to turn ambition into measurable business outcomes at scale. Supported by a robust ecosystem of partners and nearly 60 years of expertise, Capgemini is a responsible and diverse global organization of over 410,000 team members in more than 50 countries. The Group reported 2025 revenues of €22.5 billion.","description_format":"text","description_chars":4729,"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":["Home office","Hybrid work","Life insurance"],"hiring_locations":[{"name":"Poland","iso":"PL","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Cybersecurity","Government","Science & Engineering","Research Institutes"],"lifecycle":[{"event":"open","at":"2026-10-03T19:19:52Z"}],"visa":[],"liveness":{"score":20,"band":"cold","label":"Long shot","p_open":1,"p_active":0.545,"p_room":0.36,"age_days":122,"expected_fill_days":63,"reasons":["conf:1","win:tail","crowd:brand"],"computed_at":"2026-10-04T01:47:04Z"},"pay":null,"html_url":"https://alion.io/job/capgemini-ai-data-engineer-data-engineering-cloud-platform-python","json_url":"https://alion.io/job/capgemini-ai-data-engineer-data-engineering-cloud-platform-python.json","meta":{"generated_at":"2026-10-04T01:47:04Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":2433,"day_limit":5000,"remaining_today":2567,"minute_limit":60,"resets_at":"2026-10-05T00:00:00Z"}}}