{"id":1452464,"url":"https://alion.io/job/scaling-theory-technologies-senior-data-engineer","title":"Senior Data Engineer","company":{"id":3800245,"name":"ScalingTheory Technologies","domain":"scalingtheory.com","url":"https://alion.io/company/scaling-theory-technologies","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":"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":22000,"max_usd":44000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":54},"experience_years_min":14,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"CI/CD","optional":false},{"name":"Databricks","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Git","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-09-29T07:31:48Z","employer_posted_date":null,"last_verified_at":"2026-09-29T07:31:48Z","board_verified":false,"closed_at":null,"days_open":6,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":6},"description":"About the Role : \n\nWe are seeking a Senior Data Engineer (Data Engineer III) who is passionate about building modern data platforms and solving complex engineering challenges at scale. In this role, you will own data products end-to-end, from understanding business problems and designing scalable architectures to building production-grade pipelines that support analytics, AI, and operational excellence.\n\nData Product Development : \n\n- Own data products from design through production.\n\n- Design, build, and maintain scalable data pipelines and data products using Databricks, Spark, Python, SQL, and AWS.\n\n- Develop robust batch and streaming pipelines aligned with modern Lakehouse architecture principles.\n\n- Build reusable ETL/ELT frameworks, curated datasets, and self-service data products for analytics, AI/ML, and operational reporting.\n\n- Optimise pipelines for performance, scalability, reliability, and cost efficiency.\n\n- Implement incremental processing, CDC, and metadata-driven engineering frameworks.\n\nSolution Design and Architecture : \n\n- Partner with business stakeholders to understand requirements and translate them into scalable technical solutions.\n\n- Design end-to-end data architectures, reusable frameworks, and high-performance data models.\n\n- Evaluate architectural trade-offs and influence technical direction across the data platform.\n\n- Drive solution design from concept through production deployment.\n\nEngineering Excellence : \n\n- Build production-grade solutions with a strong focus on quality, testing, observability, security, and reliability.\n\n- Implement automated data validation, monitoring, lineage, and operational best practices.\n\n- Write clean, maintainable code and contribute to reusable frameworks, CI/CD, DataOps practices, and code reviews.\n\n- Troubleshoot production issues and continuously improve platform performance and developer experience.\n\nBusiness Partnership : \n\n- Collaborate with business stakeholders, product owners, analysts, architects, and engineers to solve high-impact business problems.\n\n- Translate business requirements into scalable data products and trusted datasets.\n\n- Communicate technical concepts effectively to both technical and non-technical audiences.\n\n- Take end-to-end ownership of solutions from discovery and design to production support.\n\nRequirements : \n\n- 14+ years of experience in Data Engineering, with experience delivering enterprise-scale data platforms.\n\n- Strong expertise in Databricks, Apache Spark (PySpark), Python, and SQL.\n\n- Hands-on experience building cloud-native data platforms on AWS.\n\n- Strong understanding of distributed data processing, Lakehouse architecture, ETL/ELT, and modern data engineering practices.\n\n- Experience designing scalable data models and optimising large-scale data pipelines.\n\n- Strong software engineering fundamentals, including Git, CI/CD, testing, and code quality.\n\n- Excellent communication skills with the ability to influence stakeholders and lead technical discussions.\nSkills\nDatabricks, Apache Spark, Python, SQL, AWS, Data Engineering, ETL, Data Management, Data Services, Data Pipeline","description_format":"text","description_chars":3136,"description_truncated":false,"requirements":{"experience_years_min":14,"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":["Software"],"lifecycle":[{"event":"open","at":"2026-09-29T08:00:48Z"}],"visa":[],"liveness":{"score":87,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.874,"p_room":1,"age_days":5,"expected_fill_days":23,"reasons":["seen:5","velocity","win:early"],"computed_at":"2026-10-05T05:45:15Z"},"pay":null,"html_url":"https://alion.io/job/scaling-theory-technologies-senior-data-engineer","json_url":"https://alion.io/job/scaling-theory-technologies-senior-data-engineer.json","meta":{"generated_at":"2026-10-06T01:00:34Z","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":"search","counted_by":"address","units_charged":0,"used_today":0,"day_limit":null,"remaining_today":null,"minute_limit":null,"resets_at":"2026-10-07T00:00:00Z"}},"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":3800245},"rest":"https://alion.io/mcp/rest/get_company?id=3800245"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fscaling-theory-technologies-senior-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%2Fscaling-theory-technologies-senior-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%2Fscaling-theory-technologies-senior-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/scaling-theory-technologies-senior-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fscaling-theory-technologies-senior-data-engineer"}]}