{"id":2982678,"url":"https://alion.io/job/thepsi-senior-data-engineer","title":"Senior Data Engineer","company":{"id":44642,"name":"Thepsi","domain":"thepsi.com","url":"https://alion.io/company/thepsi","size_band":"11-50","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":["Jaipur, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":19000,"max_usd":38000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":71},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Claude Code","optional":false},{"name":"Cursor","optional":false},{"name":"Databricks","optional":false},{"name":"Delta Lake","optional":false},{"name":"Embeddings","optional":false},{"name":"ETL/ELT","optional":false},{"name":"OpenAI Codex","optional":false},{"name":"pySpark","optional":false},{"name":"RAG","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"AWS","optional":true},{"name":"Azure","optional":true},{"name":"CI/CD","optional":true},{"name":"Docker","optional":true},{"name":"GCP","optional":true},{"name":"Git","optional":true},{"name":"Python","optional":true}],"status":"live","first_seen_at":"2026-10-21T07:35:00Z","employer_posted_date":null,"last_verified_at":"2026-10-21T07:35:00Z","board_verified":false,"closed_at":null,"days_open":2,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":2},"description":"We are looking for a hands-on Data Engineer with strong expertise in SQL, PySpark, Apache Spark, and Databricks, along with awareness of GenAI and AI-assisted coding tools. The candidate should be capable of building scalable data pipelines, troubleshooting performance issues, and optimizing data processing for both performance and cost.\n\nResponsibilities: \nDesign, develop, and maintain scalable data pipelines using SQL, PySpark, Spark, and Databricks.\nBuild reliable batch/incremental data-processing solutions and data products.\nTroubleshoot and optimize Spark workloads for performance, scalability, and cost efficiency.\nWork with Delta Lake and modern data-platform architecture.\nUse AI coding agents to accelerate development, debugging, testing, and documentation.\nCollaborate with application teams, consultants, and managers.\n\nRequirements: \nStrong problem-solving and analytical skills.\nHands-on, engineering-oriented mindset.\nAbility to understand why a technical approach is selected, not just implement it.\nClear and structured communication.\nComfortable working independently and learning new technologies.\nExpert SQL and PySpark development.\nStrong understanding of Apache Spark internals: distributed processing, partitioning, shuffle, data skew, and execution model.\nStrong Databricks experience with Delta Lake, optimization, compute management, and cost optimization.\nStrong data-engineering fundamentals: ETL/ELT, data modelling, incremental processing, and data quality.\nExperience troubleshooting and optimizing large-scale data workloads.\n\nGenAI and AI-Assisted Development: \nLLMs, RAG, embeddings, agents, and agentic AI.\nAI-assisted coding tools such as Claude Code, Codex, Cursor, Antigravity, or similar.\nAbility to review, validate, and improve AI-generated code.\n\nGood to Have: \nDevOps knowledge: Git, CI/CD, Docker, and deployment practices.\nExposure to NoSQL databases and their use cases.\nData Engineer/Analytics Certificate in any of the clouds (AWS, Azure, or GCP).\nSkills\nApache Spark, Databricks, PySpark, SQL, Spark","description_format":"text","description_chars":2055,"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":["IT Consulting & Digital Transformation","IT Outsourcing & Dedicated Teams","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-10-21T07:35:00Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":1,"expected_fill_days":30,"reasons":["seen:1","velocity","win:early"],"computed_at":"2026-10-23T05:54:15Z"},"pay":null,"html_url":"https://alion.io/job/thepsi-senior-data-engineer","json_url":"https://alion.io/job/thepsi-senior-data-engineer.json","meta":{"generated_at":"2026-10-23T16:20:57Z","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":24799,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-24T00:00:00Z"}},"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":44642},"rest":"https://alion.io/mcp/rest/get_company?id=44642"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fthepsi-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%2Fthepsi-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%2Fthepsi-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/thepsi-senior-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fthepsi-senior-data-engineer"}]}