{"id":1227771,"url":"https://alion.io/job/digitalcubez-data-engineerscientist","title":"Data Engineer/Scientist","company":{"id":3800776,"name":"DIgitalcubez","domain":"digitalcube-cs.com","url":"https://alion.io/company/digitalcubez-2","size_band":null,"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":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":21000,"max_usd":52000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":431},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"A/B Testing","optional":false},{"name":"Amazon SageMaker","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Hadoop","optional":false},{"name":"Machine Learning","optional":false},{"name":"Matplotlib","optional":false},{"name":"Power BI","optional":false},{"name":"Python","optional":false},{"name":"Seaborn","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Tableau","optional":false}],"status":"live","first_seen_at":"2026-09-23T06:37:42Z","employer_posted_date":null,"last_verified_at":"2026-09-23T06:37:42Z","board_verified":false,"closed_at":null,"days_open":3,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":3},"description":"Role Overview :\n\nThe Data Engineer / Data Scientist will be responsible for designing, developing, and maintaining data pipelines, performing data analysis, building predictive models, and ensuring data quality across platforms and operations.\n\nKey Responsibilities :\n\n- Design, build, and optimize scalable data pipelines and ETL processes.\n\n- Develop and maintain data models, data marts, and analytical datasets.\n\n- Collaborate with cross-functional teams to gather requirements and deliver data-driven solutions.\n\n- Perform exploratory data analysis (EDA) and create machine learning models as required.\n\n- Implement data quality checks, validation rules, and monitoring processes.\n\n- Automate data workflows and ensure timely availability of data.\n\n- Work with cloud platforms such as Azure, AWS, or GCP for data engineering activities.\n\nTechnical Skills :\n\n- Proficient in programming languages such as Python or R.\n\n- Expertise in statistics, machine learning algorithms, and data mining techniques.\n\n- Experience with data preprocessing, feature engineering, and model validation.\n\n- Skilled in data visualization tools and libraries (Tableau, Power BI, Matplotlib, Seaborn).\n\n- Familiarity with big data platforms (Spark, Hadoop) and SQL databases.\n\n- Knowledge of cloud-based ML platforms (AWS SageMaker, Azure ML, GCP AI Platform).\n\n- Understanding of experimental design and A/B Testing.\n\nQuality Testing Responsibilities :\n\n- Develop and execute data validation and data quality test cases.\n\n- Perform unit and integration testing for data pipelines.\n\n- Monitor data accuracy, completeness, and consistency across systems.\n\n- Identify data anomalies and work with engineering teams to resolve issues.\n\nMust Have :\n\n- SQL, Python, Data Science, Azure, AWS, Spark\n\nSkills\nPython, SQL, AWS, Azure, Spark, Data Science, ETL, Machine Learning, Tableau, Power BI, Data Scientist","description_format":"text","description_chars":1885,"description_truncated":false,"requirements":{"experience_years_min":4,"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":[],"lifecycle":[{"event":"open","at":"2026-09-25T13:06:44Z"}],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":2,"expected_fill_days":17,"reasons":["seen:2","win:early"],"computed_at":"2026-09-26T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/digitalcubez-data-engineerscientist","json_url":"https://alion.io/job/digitalcubez-data-engineerscientist.json","meta":{"generated_at":"2026-09-27T03:02:32Z","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":2790,"day_limit":5000,"remaining_today":2210,"minute_limit":60,"resets_at":"2026-09-28T00:00:00Z"}}}