{"id":4314972,"url":"https://alion.io/job/datavruti-senior-databricks-data-engineer-pyspark-bangalore","title":"Senior Databricks Data Engineer - PySpark - Bangalore","company":{"id":4489938,"name":"datavruti","domain":"datavruti.com","url":"https://alion.io/company/datavruti","size_band":"51-200","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Schema","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":{"min":null,"max":2500000,"currency":"INR","period":"year","gross":null,"usd_annual":26662},"salary_estimate":null,"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Databricks","optional":false},{"name":"ETL/ELT","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Snowflake","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Agile","optional":true},{"name":"AWS","optional":true},{"name":"Azure","optional":true},{"name":"CI/CD","optional":true},{"name":"Hadoop","optional":true}],"status":"live","first_seen_at":"2026-09-28T13:05:52Z","employer_posted_date":"2026-09-28","last_verified_at":"2026-11-22T10:49:20Z","board_verified":true,"closed_at":null,"days_open":54,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":54},"description":"Hiring for: A technology company delivering enterprise data engineering and analytics solutions, with a strong focus on modern cloud data platforms and Databricks.\nRole: Senior Databricks Data Engineer - PySpark - Bangalore/ Pune\nPositions: 10\nExperience: 4 to 7 years\nLocation(s): Remote (Bangalore, Pune)\nType: On-site, Remote / Permanent\nSalary: Up to INR 25 LPA\nNotice Period: Immediate to 30 days\nMust Have: Databricks Development, Pyspark, Python, SQL, Unity Catalogs,\nJob Summary\nWe are seeking an experienced PySpark ETL Developer with 4+ years of experience in designing, developing, and optimizing enterprise ETL pipelines using PySpark. The ideal candidate should have strong expertise in Python, Apache Spark, Databricks, and Snowflake, along with hands-on experience in processing large-scale data and building scalable data engineering solutions. You will work closely with business stakeholders and cross-functional teams to develop high-performance data pipelines that support business intelligence and analytics initiatives.\nKey Responsibilities\nDesign, develop, and maintain scalable ETL pipelines using PySpark and Spark SQL.\nCollaborate with stakeholders to gather business requirements and translate them into efficient data engineering solutions.\nExtract data from multiple sources, including databases, APIs, data lakes, files, and streaming platforms.\nTransform, cleanse, and validate data using PySpark to ensure high data quality and consistency.\nDevelop and optimize Spark jobs for performance, scalability, and efficient resource utilization.\nBuild and maintain batch and streaming data pipelines to support real-time and near real-time processing.\nLoad transformed data into data lakes, data warehouses, and analytical platforms.\nImplement robust error handling, logging, monitoring, and troubleshooting mechanisms for ETL workflows.\nDocument ETL processes, data lineage, transformation logic, and technical specifications.\nDevelop unit, integration, and performance tests to ensure reliable and accurate data processing.\nCollaborate with cross-functional teams to deliver scalable, secure, and high-quality data solutions.\nRequired Skills\n4+ years of experience as a Data Engineer or ETL Developer.\nStrong hands-on experience with PySpark, Apache Spark, Spark SQL, and Python.\nExpertise in Databricks.\nStrong understanding of ETL design, data transformation, and data integration.\nExperience with Data Lakes, Data Warehouses, and Big Data technologies.\nKnowledge of distributed computing, parallel processing, and data partitioning concepts.\nStrong SQL skills with experience in performance tuning and query optimization.\nExperience working with batch and streaming data processing.\nExcellent analytical, debugging, and problem-solving skills.\nStrong verbal and written communication skills.\nPreferred Skills\nExperience with cloud platforms such as AWS or Azure.\nKnowledge of Hadoop ecosystem and modern data engineering technologies.\nExperience with API integration and data ingestion from multiple data sources.\nFamiliarity with CI/CD pipelines and Agile development methodologies.\nExposure to enterprise-scale data engineering projects.","description_format":"text","description_chars":3169,"description_truncated":false,"requirements":{"experience_years_min":4,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-11-14T15:19:30Z"}],"visa":[],"liveness":{"score":24,"band":"cold","label":"Long shot","p_open":1,"p_active":0.434,"p_room":0.55,"age_days":52,"expected_fill_days":38,"reasons":["conf:1","agency","velocity","win:tail"],"computed_at":"2026-11-20T05:46:30Z"},"pay":{"stated_usd_annual":26662,"is_top_pay":false},"html_url":"https://alion.io/job/datavruti-senior-databricks-data-engineer-pyspark-bangalore","json_url":"https://alion.io/job/datavruti-senior-databricks-data-engineer-pyspark-bangalore.json","meta":{"generated_at":"2026-11-22T11:04:12Z","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":17665,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-23T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"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":4489938},"rest":"https://alion.io/mcp/rest/get_company?id=4489938"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fdatavruti-senior-databricks-data-engineer-pyspark-bangalore"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"free","price":{"credits":0,"usd":0},"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%2Fdatavruti-senior-databricks-data-engineer-pyspark-bangalore"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"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%2Fdatavruti-senior-databricks-data-engineer-pyspark-bangalore"},{"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/datavruti-senior-databricks-data-engineer-pyspark-bangalore\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fdatavruti-senior-databricks-data-engineer-pyspark-bangalore"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4314972}},{"tool":"search_jobs","arguments":{"company":"datavruti.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4314972},"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"}}