{"id":560798,"url":"https://alion.io/job/inito-data-engineer","title":"Data Engineer","company":{"id":9126,"name":"Inito","domain":"inito.com","url":"https://alion.io/company/inito","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":null,"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":18000,"max_usd":49000,"period":"year","method":"role_country_seniority_unknown","sample_n":171},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CI/CD","optional":false},{"name":"Docker","optional":false},{"name":"GCP","optional":false},{"name":"Google BigQuery","optional":false},{"name":"Machine Learning","optional":false},{"name":"Metaflow","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"SQL","optional":false},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2026-09-09T04:21:10Z","employer_posted_date":null,"last_verified_at":"2026-09-09T04:21:10Z","board_verified":false,"closed_at":null,"days_open":56,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":56},"description":"Responsibilities:\nDesign, develop, and maintain robust data pipelines using Airflow, DBT, and Python within a BigQuery environment.\nImplement and maintain data integrations with various sources and targets using tools like Airbyte, Elementary, and Metaflow, with a focus on optimizing data storage and retrieval in BigQuery.\nWrite advanced SQL queries and scripts for data manipulation and retrieval in BigQuery.\nDevelop and optimize data models and schemas in Preset and other visualization tools, tailored for performance in BigQuery.\nUtilize Pyspark for big data processing tasks, ensuring compatibility with BigQuery's infrastructure.\nWork with APIs, Docker, and GCP services to enhance and automate data workflows, particularly focusing on integration with BigQuery.\nApply best practices in continuous integration and continuous deployment (CI/CD) environments using testing and pipeline validation techniques.\nEmploy asynchronous architectures, queues, caching strategies, and distributed computing to enhance system performance.\nWrite custom code in Python and utilize Jinja within DBT for dynamic pipeline generation, specifically designed for efficiency in BigQuery.\nAdopt design patterns and engineering best practices to ensure code scalability and maintainability.\nKey outcomes:\nDevelop a Unified Data Foundation: Spearheaded the creation of a single source of truth that centralizes our data assets, ensuring consistency and reliability across the board.\nDrive Impact Across Teams: Your work will directly influence the success of our business analysts, data scientists, and machine learning engineers by providing them with the crucial data they need to excel.\nOptimize Business Logic: Design and manage data tables that support and enhance business logic functions, delivering tailored data solutions that drive strategic decision-making.","description_format":"text","description_chars":1853,"description_truncated":false,"requirements":{"experience_years_min":null,"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":["Diagnostic Tests & IVD","Women’s Health & Maternity"],"lifecycle":[{"event":"open","at":"2026-09-09T04:21:10Z"}],"visa":[],"liveness":{"score":7,"band":"cold","label":"Long shot","p_open":0.4,"p_active":0.477,"p_room":0.35,"age_days":56,"expected_fill_days":25,"reasons":["seen:56","win:tail"],"computed_at":"2026-11-04T06:34:25Z"},"pay":null,"html_url":"https://alion.io/job/inito-data-engineer","json_url":"https://alion.io/job/inito-data-engineer.json","meta":{"generated_at":"2026-11-04T09:03:53Z","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":14129,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-05T00:00:00Z"}},"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":9126},"rest":"https://alion.io/mcp/rest/get_company?id=9126"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Finito-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%2Finito-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%2Finito-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/inito-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Finito-data-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":560798}},{"tool":"search_jobs","arguments":{"company":"inito.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":560798},"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"}}