{"id":1952403,"url":"https://alion.io/job/atyeti-lead-big-data-engineer","title":"Lead Big Data Engineer","company":{"id":3800820,"name":"ATYETI","domain":"atyeti.com","url":"https://alion.io/company/atyeti","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":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["India"],"countries":["IN"],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":27000,"max_usd":48000,"period":"year","method":"role_seniority_country_cell","sample_n":16},"experience_years_min":7,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon S3","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"Databricks","optional":false},{"name":"Delta Lake","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Git","optional":false},{"name":"Hadoop","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-10-06T09:58:46Z","employer_posted_date":null,"last_verified_at":"2026-10-06T09:58:46Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"Key Responsibilities : \n\n- Design and execute Hadoop to Databricks migration strategies for large-scale data platforms.\n\n- Migrate existing HDFS, Hive, Spark, and MapReduce workloads to Databricks.\n\n- Data Engineering - Hadoop to Databricks migration experience.\n\n- Strong hands-on experience in migrating and optimizing Spark code.\n\n- Analyze existing Hadoop/Spark applications and identify opportunities for modernization and optimization.\n\n- Strong hands-on experience in migrating, refactoring, and optimizing Spark code for Databricks.\n\n- Develop scalable ETL/ELT pipelines using Spark, SQL, and Databricks.\n\n- Optimize Spark jobs by improving partitioning, caching, joins, shuffling, serialization, and memory utilization.\n\n- Work with Databricks Delta Lake / Delta tables for reliable and scalable data processing.\n\n- Implement Delta Lake features such as ACID transactions, schema evolution, time travel, and optimized data layouts.\n\n- Convert legacy Hive SQL / Spark SQL workloads to Databricks SQL and optimize queries.\n\n- Migrate data from HDFS/Hive to cloud-based storage and Databricks.\n\n- Experience with Azure Data Lake Storage (ADLS), AWS S3, or equivalent cloud storage.\n\n- Develop and maintain robust data pipelines using Databricks Workflows and job orchestration tools.\n\n- Implement data quality, validation, reconciliation, and error-handling frameworks during migration.\n\n- Perform source-to-target mapping, data profiling, transformation analysis, and migration validation.\n\n- Troubleshoot performance issues across Spark clusters, notebooks, jobs, and data pipelines.\n\n- Work closely with architects, business analysts, data scientists, and application teams to understand data requirements.\n\n- Implement CI/CD practices for Databricks notebooks, jobs, and code using Git and DevOps tools.\n\n- Follow enterprise security, governance, audit, and compliance standards applicable to banking environments.\n\n- Ensure migrated workloads meet performance, scalability, availability, and data-quality requirements.\nSkills\nBig Data, Data Engineering, Hadoop, Databricks, HDFS, Hive, Spark, ETL, SQL, DataLake, Data Migration","description_format":"text","description_chars":2138,"description_truncated":false,"requirements":{"experience_years_min":7,"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":["DevOps & Platform Engineering","IT Consulting & Digital Transformation","AI Consulting & Integration"],"lifecycle":[{"event":"open","at":"2026-10-06T10:29:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":0,"expected_fill_days":26,"reasons":["seen:0","velocity","win:early"],"computed_at":"2026-10-07T05:47:15Z"},"pay":null,"html_url":"https://alion.io/job/atyeti-lead-big-data-engineer","json_url":"https://alion.io/job/atyeti-lead-big-data-engineer.json","meta":{"generated_at":"2026-10-08T00:40:26Z","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","counted_by":"address","units_charged":1,"used_today":1064,"day_limit":5000,"remaining_today":3936,"minute_limit":60,"resets_at":"2026-10-09T00:00:00Z"}},"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":3800820},"rest":"https://alion.io/mcp/rest/get_company?id=3800820"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fatyeti-lead-big-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%2Fatyeti-lead-big-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%2Fatyeti-lead-big-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/atyeti-lead-big-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fatyeti-lead-big-data-engineer"}]}