{"id":1227837,"url":"https://alion.io/job/gethyr-data-engineer","title":"Data Engineer","company":{"id":3800686,"name":"GetHyr","domain":"gethyr.com","url":"https://alion.io/company/gethyr","size_band":null,"is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"senior","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"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":21000,"max_usd":44000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":51},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Neo4j","optional":false},{"name":"Power BI","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Snowflake","optional":false},{"name":"SQL","optional":false},{"name":"Tableau","optional":false},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2026-09-23T04:12:11Z","employer_posted_date":null,"last_verified_at":"2026-09-23T04:12:11Z","board_verified":false,"closed_at":null,"days_open":8,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":8},"description":"Introduction :\n\nJoining an existing data engineering squad as staff augmentation, you bring graph data modeling and analytics skills on top of a PySpark/SQL data engineering foundation, working within the squad's existing lead and stand-ups.\n\nAs an embedded Data Engineer, you bring graph analytics to life on top of a PySpark/Snowflake data foundation.\n\nNote: Shares a common PySpark/Snowflake base with \"Data Engineer - Power BI Modelling\" - source together, differentiate on graphing vs. semantic-modeling depth at interview.\n\nKey responsibilities :\n\n- Model graph data: Design and implement graph data models and analytics (e.g., Neo4j or similar).\n\n- Build pipelines: Develop PySpark/Python and SQL pipelines feeding the Snowflake environment.\n\n- Integrate with reporting: Support Power BI consumption of graph and pipeline outputs where needed.\n\n- Collaborate: Operate inside the existing squad structure with no separate delivery lead required.\n\n- Ensure quality: Validate data accuracy and performance of graph queries and pipelines.\n\n- Explore GenAI: Apply GenAI techniques to relevant use cases as opportunities arise.\n\nMust-have qualifications :\n\n- Python and PySpark\n\n- SQL\n\n- Graph data modeling / graph databases\n\nPreferred :\n\n- Power BI (optional, depending on seniority)\n\n- Snowflake; Dataiku\n\nSkills\nPython, PySpark, SQL, Neo4j, Dataiku, Tableau, Data Modeling, Snowflake DB","description_format":"text","description_chars":1391,"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":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-09-25T13:06:44Z"}],"liveness":{"score":47,"band":"ok","label":"Likely open","p_open":1,"p_active":0.469,"p_room":1,"age_days":8,"expected_fill_days":24,"reasons":["seen:8","agency","velocity","win:early"],"computed_at":"2026-10-01T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/gethyr-data-engineer","json_url":"https://alion.io/job/gethyr-data-engineer.json","meta":{"generated_at":"2026-10-01T20:54:20Z","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":3324,"day_limit":5000,"remaining_today":1676,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}