{"id":1280028,"url":"https://alion.io/job/curebay-data-engineer","title":"Data Engineer","company":{"id":3801536,"name":"Curebay","domain":"curebay.com","url":"https://alion.io/company/curebay","size_band":"51-200","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":"junior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India","India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":13500,"max_usd":32000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":9},"experience_years_min":1,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Git","optional":false},{"name":"Jupyter Notebook","optional":false},{"name":"Python","optional":false},{"name":"SQL","optional":false},{"name":"Amazon Redshift","optional":true},{"name":"AWS","optional":true},{"name":"Azure","optional":true},{"name":"BigQuery","optional":true},{"name":"Docker","optional":true},{"name":"GCP","optional":true},{"name":"Google BigQuery","optional":true},{"name":"NumPy","optional":true},{"name":"Pandas","optional":true},{"name":"pySpark","optional":true},{"name":"Snowflake","optional":true},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2026-08-21T06:10:01Z","employer_posted_date":null,"last_verified_at":"2026-08-21T06:10:01Z","board_verified":false,"closed_at":null,"days_open":40,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":40},"description":"About the Role :\n\nWe're looking for a Data Engineer with 1 - 2 years of experience to join our data team. You'll help build, maintain, and optimize data pipelines that power analytics and decision-making across the organization. This is a great opportunity for someone early in their career who wants to deepen their skills in workflow orchestration, data pipeline design, and Python-based data engineering.\n\nKey Responsibilities :\n\n- Design, build, and maintain ETL/ELT data pipelines using Apache Airflow.\n\n- Write clean, efficient, and reusable Python code for data processing and transformation.\n\n- Use Jupyter Notebooks for data exploration, prototyping, and validation of pipeline logic.\n\n- Monitor pipeline performance, troubleshoot failures, and ensure data quality and reliability.\n\n- Collaborate with data analysts, data scientists, and other engineers to understand data requirements.\n\n- Maintain and improve existing DAGs, including scheduling, dependency management, and error handling.\n\n- Document pipelines, workflows, and processes for team-wide visibility.\n\n- Assist in optimizing SQL queries and database performance where needed.\n\nRequired Skills & Qualifications :\n\n- 1 - 2 years of hands-on experience in data engineering or a related role.\n\n- Proficiency in Apache Airflow (DAG creation, scheduling, operators, task dependencies).\n\n- Strong working knowledge of Python for scripting and data manipulation.\n\n- Experience using Jupyter Notebook for data analysis/prototyping.\n\n- Familiarity with SQL and relational databases.\n\n- Understanding of ETL/ELT concepts and data pipeline best practices.\n\n- Basic knowledge of version control (Git).\n\nNice to Have :\n\n- Experience with cloud platforms (AWS / GCP / Azure).\n\n- Familiarity with data warehousing tools (Snowflake, BigQuery, Redshift, etc.).\n\n- Exposure to libraries like Pandas, NumPy, or PySpark.\n\n- Understanding of data modeling concepts.\n\n- Experience with containerization (Docker).\n\nSkills\nData Engineering, Python, Apache Airflow, SQL, Data Management, Pandas, Numpy, Spark","description_format":"text","description_chars":2055,"description_truncated":false,"requirements":{"experience_years_min":1,"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":["Health Care","Medical Laboratories"],"lifecycle":[{"event":"open","at":"2026-09-26T02:00:24Z"}],"liveness":{"score":18,"band":"cold","label":"Long shot","p_open":0.6,"p_active":0.543,"p_room":0.55,"age_days":39,"expected_fill_days":30,"reasons":["seen:39","win:tail","comp:junior"],"computed_at":"2026-09-30T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/curebay-data-engineer","json_url":"https://alion.io/job/curebay-data-engineer.json","meta":{"generated_at":"2026-10-01T05:05:11Z","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":4715,"day_limit":5000,"remaining_today":285,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}