{"id":1146662,"url":"https://alion.io/job/itds-poland-mid-level-data-scientist-machine-learning-pipelines","title":"Mid-Level Data Scientist - Machine Learning Pipelines","company":{"id":879,"name":"ITDS Poland","domain":"itds.pl","url":"https://alion.io/company/itds","size_band":"201-500","is_staffing_agency":false,"employer_type":"staffing","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"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":["Kraków, Poland"],"countries":["PL"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":22470,"max":27090,"currency":"PLN","period":"month","gross":null,"usd_annual":85008},"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"LightGBM","optional":false},{"name":"Machine Learning","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"XGBoost","optional":false}],"status":"live","first_seen_at":"2026-09-23T14:20:10Z","employer_posted_date":null,"last_verified_at":"2026-09-23T14:20:10Z","board_verified":false,"closed_at":null,"days_open":4,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":4},"description":"Unleash innovation with data-drive transformative insights through advanced machine learning!\nKraków-based opportunity with hybrid work model (2 days in office, 3 days remote).\nAs a Mid-Level Data Scientist, you will be working for our client to develop and optimize cutting-edge machine learning pipelines. Join their team to shape intelligent solutions that impact business decisions and foster technological progress.\nYour main responsibilities:\nSupport the ML team with feature engineering, model selection, training, validation, and testing\nAnalyze datasets to evaluate their suitability and contribution to projects\nCollaborate closely with data scientists and data engineers to enhance pipeline performance\nYou're ideal for this role if you have:\nAt least 3 years of experience in classical ML pipelines\nHands-on knowledge in feature engineering and models such as XGBoost, LightGBM, MLP, autoencoders, etc.\nAdvanced SQL skills in standard language and proficiency with Python APIs (PySpark, pandas)\nA detail-oriented and diligent personality with excellent communication skills\nIt is a strong plus if you have: (optional)\nKnowledge of Apache Spark\nLanguage Required for the role :\nCommunicative English\nEligibility for the role :\nOnly candidates with an existing legal right to work in the European Union will be considered for this role.\n#MAKEYourCareerBETTER\nInterested? Apply now and include your CV (preferably in English) along with a statement confirming your consent to the processing and storage of your personal data.","description_format":"text","description_chars":1534,"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":[{"language":"English","level":"Upper-Intermediate (B2)","optional":false}]},"benefits":["Hybrid work"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Consulting & Digital Transformation","IT Staffing & Staff Augmentation"],"lifecycle":[{"event":"open","at":"2026-09-23T15:33:13Z"}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":3,"expected_fill_days":43,"reasons":["seen:3","velocity","win:early"],"computed_at":"2026-09-27T05:45:00Z"},"pay":{"stated_usd_annual":85008,"is_top_pay":false},"html_url":"https://alion.io/job/itds-poland-mid-level-data-scientist-machine-learning-pipelines","json_url":"https://alion.io/job/itds-poland-mid-level-data-scientist-machine-learning-pipelines.json","meta":{"generated_at":"2026-09-28T05:17:39Z","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":3530,"day_limit":5000,"remaining_today":1470,"minute_limit":60,"resets_at":"2026-09-29T00:00:00Z"}}}