{"id":1230154,"url":"https://alion.io/job/supersourcing-data-engineer","title":"Data Engineer","company":{"id":59528,"name":"Supersourcing","domain":"supersourcing.com","url":"https://alion.io/company/supersourcing","size_band":"11-50","is_staffing_agency":true,"employer_type":"agency","is_intermediary":true,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":null,"work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["Pune, India","Bengaluru, India","Hyderabad, India","India"],"countries":["IN"],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":21000,"max_usd":42000,"period":"year","method":"role_seniority_country_cell","sample_n":57},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Databricks","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Microsoft Fabric","optional":false},{"name":"Power BI","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-09-21T05:42:56Z","employer_posted_date":null,"last_verified_at":"2026-09-21T05:42:56Z","board_verified":false,"closed_at":null,"days_open":8,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":8},"description":"Key Responsibilities : \n\n- Develop and maintain scalable data pipelines using Databricks and Apache Spark.\n\n- Build, optimize, and maintain ETL/data processing pipelines for large-scale data workloads.\n\n- Perform data extraction, transformation, and processing using Python, PySpark, and SQL.\n\n- Design and implement data models and data warehousing solutions.\n\n- Develop and optimize Databricks notebooks for data processing, exploration, and analysis.\n\n- Monitor pipeline performance and troubleshoot data processing and performance issues.\n\n- Collaborate with data scientists, data analysts, and business stakeholders to deliver data solutions.\n\n- Support analytics, reporting, and BI initiatives using Power BI.\n\n- Work with cloud-based data platforms and services across AWS, Azure, or GCP.\n\n- Ensure data quality, reliability, and performance across data engineering workflows.\n\nTech Stack : \n\n- Databricks, Python, PySpark/Apache Spark, SQL, Power BI, AWS/Azure/GCP.\n\nAdditional Requirements : \n\n- Willingness to work remotely with office visits to Pune, Bangalore, or Hyderabad whenever required based on business/project needs.\n\n- Availability for weekend interview drives may be required based on the hiring schedule.\n\nSkills\nDatabricks, Python, Apache Spark, SQL, ETL, Data Engineering, Data Warehousing, Microsoft Fabric, Data Modeling","description_format":"text","description_chars":1347,"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":[],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-09-25T14:00:00Z"}],"liveness":{"score":14,"band":"cold","label":"Long shot","p_open":1,"p_active":0.24,"p_room":0.578,"age_days":8,"expected_fill_days":7,"reasons":["seen:8","agency","velocity","win:tail"],"computed_at":"2026-09-29T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/supersourcing-data-engineer","json_url":"https://alion.io/job/supersourcing-data-engineer.json","meta":{"generated_at":"2026-09-30T05:29:07Z","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":3843,"day_limit":5000,"remaining_today":1157,"minute_limit":60,"resets_at":"2026-10-01T00:00:00Z"}}}