{"id":2771436,"url":"https://alion.io/job/tvarit-data-engineer","title":"Data Engineer","company":{"id":2099587,"name":"Tvarit","domain":"tvarit.com","url":"https://alion.io/company/tvarit","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Keka","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"junior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":1200000,"max":1600000,"currency":"INR","period":"year","gross":null,"usd_annual":16829},"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"Databricks","optional":false},{"name":"Docker","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Kubernetes","optional":false},{"name":"pySpark","optional":false},{"name":"Spark","optional":false},{"name":"Cassandra","optional":true},{"name":"InfluxDB","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Python","optional":true},{"name":"SQL","optional":true},{"name":"Time Series Forecasting","optional":true}],"status":"live","first_seen_at":"2025-11-14T05:55:34Z","employer_posted_date":"2025-11-14","last_verified_at":"2026-10-18T05:08:25Z","board_verified":true,"closed_at":null,"days_open":338,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":337},"description":"Job Title: Data Engineer\nLocation: Pune\nJob Type: Full-Time ( WFO )\nAbout TVARIT\nTVARIT GmbH specializes in developing and delivering cutting-edge artificial intelligence (AI) solutions for the metal industry, including steel, aluminum, copper, cast iron, and more. Our software products empower customers to make intelligent, data-driven decisions, driving advancements in Predictive Quality (PsQ), Predictive Maintenance (PdM), and Energy Consumption Reduction (PsE), etc.\nWith a strong portfolio of renowned reference customers, state-of-the-art technology, a talented research team from prestigious universities, and recognition through esteemed awards such as the EU Horizon 2020 AI Prize, TVARIT is recognized as one of the most innovative AI companies in Germany and Europe.\nWe are seeking a self-motivated individual with a positive \"can-do\" attitude and excellent oral and written communication skills in English to join our team.\nJob Description\nWe are looking for a Data Engineer with strong expertise in Azure Databricks, PySpark, and distributed computing to develop and optimize scalable ETL pipelines for manufacturing analytics. The role involves working with high-frequency industrial data to enable real-time and batch data processing.\nKey Responsibilities\nBuild scalable real-time and batch processing workflows using Azure Databricks, PySpark, and Apache Spark.\nPerform data pre-processing, including cleaning, transformation, deduplication, normalization, encoding, and scaling to ensure high-quality input for downstream analytics.\nDesign and maintain cloud-based data architectures, including data lakes, lakehouses, and warehouses, following Medallion Architecture.\nDeploy and optimize data solutions on Azure (preferred), AWS, or GCP, with a focus on performance, security, and scalability.\nDevelop and optimize ETL/ELT pipelines for structured and unstructured data from IoT, MES, SCADA, LIMS, and ERP systems.\nAutomate data workflows using CI/CD and DevOps best practices, ensuring security and compliance with industry standards.\nMonitor, troubleshoot, and enhance data pipelines for high availability and reliability.\nUtilize Docker and Kubernetes for scalable data processing.\nCollaborate with the automation team, data scientists, and engineers to provide clean, structured data for AI/ML models.\nDesired Skills and Qualifications\nBachelor’s or Master’s degree in Computer Science, Information Technology, or a related field.\nMinimum 2 years of experience in data engineering, with a strong focus on cloud platforms such as Azure (preferred), AWS, or GCP.\nProficiency in PySpark, Azure Databricks, Python, and Apache Spark.\nExpertise in relational databases (e.g., SQL Server, PostgreSQL), time-series databases (e.g., InfluxDB), and NoSQL databases (e.g., MongoDB, Cassandra).\nExperience in containerization (Docker, Kubernetes).\nStrong analytical and problem-solving skills with attention to detail.\nGood to have knowledge of MLOps, DevOps, and model lifecycle management.\nExcellent communication and collaboration skills, with a proven ability to work effectively as a team player.\nComfortable working in a dynamic, fast-paced startup environment, adapting quickly to changing priorities and responsibilities.","description_format":"text","description_chars":3243,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[{"language":"English","level":"All levels","optional":false}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Manufacturing","Industrial AI"],"lifecycle":[{"event":"open","at":"2026-10-17T06:28:26Z"}],"visa":[],"liveness":{"score":2,"band":"cold","label":"Long shot","p_open":1,"p_active":0.088,"p_room":0.28,"age_days":338,"expected_fill_days":19,"reasons":["conf:2","win:tail","crowd:junior"],"computed_at":"2026-10-18T07:18:57Z"},"pay":{"stated_usd_annual":16829,"is_top_pay":false},"html_url":"https://alion.io/job/tvarit-data-engineer","json_url":"https://alion.io/job/tvarit-data-engineer.json","meta":{"generated_at":"2026-10-18T07:18:57Z","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":10955,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-19T00:00:00Z"}},"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":2099587},"rest":"https://alion.io/mcp/rest/get_company?id=2099587"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Ftvarit-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%2Ftvarit-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%2Ftvarit-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/tvarit-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftvarit-data-engineer"}]}