{"id":3241908,"url":"https://alion.io/job/purplle-data-engineer","title":"Data Engineer","company":{"id":3795,"name":"Purplle","domain":"purplle.com","url":"https://alion.io/company/purplle","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":"middle","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Mumbai, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":13500,"max_usd":36000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":21},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Apache Kafka","optional":false},{"name":"Databricks","optional":false},{"name":"Feature Store","optional":false},{"name":"Flink","optional":false},{"name":"GCP","optional":false},{"name":"Google BigQuery","optional":false},{"name":"Java","optional":false},{"name":"Python","optional":false},{"name":"Recommender Systems","optional":false},{"name":"Scala","optional":false},{"name":"Self-Healing","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Airflow","optional":true},{"name":"Amazon S3","optional":true},{"name":"AWS","optional":true},{"name":"Claude","optional":true},{"name":"Cursor","optional":true},{"name":"dbt","optional":true},{"name":"Docker","optional":true},{"name":"Great Expectations","optional":true},{"name":"Kubernetes","optional":true},{"name":"Terraform","optional":true}],"status":"live","first_seen_at":"2026-10-25T16:35:00Z","employer_posted_date":null,"last_verified_at":"2026-10-25T16:35:00Z","board_verified":false,"closed_at":null,"days_open":3,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":3},"description":"Responsibilities: \nAI-Augmented Pipeline Architecture: Design and build self-healing, schema-validated data pipelines on GCP (BigQuery, Dataflow, Pub/Sub) that power real-time analytics. Pipelines must be idempotent, observable, and auto-recover from failures without human intervention.\nStreaming and Batch Processing at Scale: Implement and optimise large-scale processing workflows using Apache Spark, Flink, or Beam. Own both real-time Kafka consumer pipelines and scheduled batch jobs, ensuring sub-hour SLAs for data freshness across all critical business domains.\nSchema Contracts and Data Integrity: Implement and enforce schema registry and data contract standards across all producers and consumers: target 100% data quality scores, no silent failures, and no downstream surprises.\nML Pipeline Integration: Build and maintain feature stores and data pipelines that feed production ML models (recommender systems, demand forecasting, pricing). Collaborate with data science to ensure training-serving skew is eliminated.\nData Governance and Cost Engineering: Champion data cataloguing, lineage tracking, and access-control policies. Monitor BigQuery slot usage and pipeline costs, and implement optimisations that reduce cloud spend by measurable percentages each quarter.\n\nRequirements: \nDE2 3-6 years; end-to-end ownership of production pipelines at scale.\nAbility to ship data products independently with clear quality and latency guarantees.\n\nTech Stack: \nLanguages: Python, Scala, Java, SQL.\nProcessing: Apache Spark, Apache Beam / Dataflow, Apache Flink, Kafka, Databricks.\nCloud and Storage: GCP (BigQuery, Dataflow, Pub/Sub, DataProc, and GCS) and AWS (S3 and EMR).\nOrchestration: Apache Airflow (Cloud Composer).\nData Quality: Great Expectations, dbt.\nInfrastructure: Kubernetes, Docker, Terraform, Databricks.\nAI Productivity: Cursor, Claude.\nSkills\nairflow, beam, bigquery, databricks, dataflow, flink, gcp, java, kafka, pub/sub, python, scala, spark, sql","description_format":"text","description_chars":1975,"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":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["E-commerce Platforms","Cosmetics & Makeup","Skincare"],"lifecycle":[{"event":"open","at":"2026-10-25T16:35:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":2,"expected_fill_days":30,"reasons":["seen:2","velocity","win:early"],"computed_at":"2026-10-28T05:59:10Z"},"pay":null,"html_url":"https://alion.io/job/purplle-data-engineer","json_url":"https://alion.io/job/purplle-data-engineer.json","meta":{"generated_at":"2026-10-29T02:09:03Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":3217,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-30T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":3795},"rest":"https://alion.io/mcp/rest/get_company?id=3795"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fpurplle-data-engineer"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fpurplle-data-engineer"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fpurplle-data-engineer"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/purplle-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fpurplle-data-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3241908}},{"tool":"search_jobs","arguments":{"company":"purplle.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3241908},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}