{"id":1239001,"url":"https://alion.io/job/prosapiens-lead-data-engineer","title":"Lead Data Engineer","company":{"id":3802040,"name":"Prosapiens","domain":"prosapiens.co.in","url":"https://alion.io/company/prosapiens-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":"lead","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":28000,"max_usd":60000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":20},"experience_years_min":6,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"CI/CD","optional":false},{"name":"Docker","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Git","optional":false},{"name":"Kubernetes","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Rest API","optional":false},{"name":"SQL","optional":false},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2026-09-16T12:17:51Z","employer_posted_date":null,"last_verified_at":"2026-09-16T12:17:51Z","board_verified":false,"closed_at":null,"days_open":34,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":34},"description":"We're Hiring : Lead Data Engineer - Supply Chain\n\nRole : Lead Data Engineer\n\nDomain : Data Engineering | Supply Chain | AI\n\nExperience : 6+ Years\n\nLocation : Pune\n\nWork Mode : Hybrid\n\nAbout the Role : \n\nWe are looking for an experienced Lead Data Engineer with strong hands-on expertise in Data Engineering and Supply Chain to design and build scalable, real-time, and batch data platforms. The ideal candidate should have strong experience in Python, PySpark, Advanced SQL, data transformations, system integrations, and Supply Chain workflows, along with exposure to AI and Agentic solutions.\n\nKey Responsibilities : \n\n- Design and build real-time and batch data ingestion pipelines for AI-based Supply Chain solutions.\n\n- Develop complex data transformation, cleansing, enrichment, and reconciliation workflows.\n\n- Integrate data from REST APIs, databases, files, enterprise systems, and streaming sources.\n\n- Develop ETL tools and validation routines for complex Supply Chain workflows.\n\n- Build reusable Python and SQL components for ingestion and transformation.\n\n- Implement schema evolution, incremental loads, retries, error handling, and data recovery.\n\n- Understand agentic structures and create data solutions/models for optimization engines.\n\n- Implement data quality checks, monitoring, logging, alerting, and audit controls.\n\n- Review technical designs and guide data engineers on implementation standards.\n\nRequired Skills : \n\n- 6+ years of hands-on experience in Data Engineering\n\n- Strong experience with Supply Chain data management and transformation\n\n- Strong Python & PySpark development skills\n\n- Advanced SQL, including complex joins and query optimization\n\n- Strong understanding of ETL/ELT design patterns\n\n- Experience with REST APIs, JSON, CSV, MongoDB, and OLAP engines\n\n- Experience developing Agents and Agentic solutions/designs\n\n- Strong understanding of data modelling, schema design, partitioning, and schema evolution\n\n- Experience with pipeline observability, data validation, monitoring, and alerting\n\n- Hands-on experience with Git, CI/CD, Docker, and Kubernetes\n\n- References would be highly appreciated!\n\nSkills\nData Engineering, Python, PySpark, SQL, Data Ingestion, Data Quality, Data Validation, MongoDB, ETL","description_format":"text","description_chars":2252,"description_truncated":false,"requirements":{"experience_years_min":6,"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":"2026-09-25T16:00:00Z"}],"visa":[],"liveness":{"score":21,"band":"cold","label":"Long shot","p_open":0.6,"p_active":0.635,"p_room":0.55,"age_days":33,"expected_fill_days":26,"reasons":["seen:33","win:tail"],"computed_at":"2026-10-20T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/prosapiens-lead-data-engineer","json_url":"https://alion.io/job/prosapiens-lead-data-engineer.json","meta":{"generated_at":"2026-10-20T21:23:17Z","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":24844,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-21T00:00:00Z"}},"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":3802040},"rest":"https://alion.io/mcp/rest/get_company?id=3802040"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fprosapiens-lead-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%2Fprosapiens-lead-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%2Fprosapiens-lead-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/prosapiens-lead-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fprosapiens-lead-data-engineer"}]}