{"id":3133394,"url":"https://alion.io/job/cummins-data-scientist-senior-3","title":"Data Scientist - Senior","company":{"id":1758413,"name":"Cummins","domain":"cummins.com","url":"https://alion.io/company/cummins-com","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Oracle","truth_index":{"grade":"B","score":83,"open_postings":70,"ghost_share":0,"stale_share":0.886,"repost_share":0,"time_to_fill_p50_days":15,"computed_at":"2026-10-24T06:02:35Z"}},"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":["Pune, 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":8,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agile","optional":false},{"name":"Apache Iceberg","optional":false},{"name":"Apache Kafka","optional":false},{"name":"Azure","optional":false},{"name":"Azure SQL Database","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":"HBase","optional":false},{"name":"Java","optional":false},{"name":"Jenkins","optional":false},{"name":"Kanban","optional":false},{"name":"Platform Engineering","optional":false},{"name":"Python","optional":false},{"name":"Replicate","optional":false},{"name":"Scala","optional":false},{"name":"Scrum","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Machine Learning","optional":true},{"name":"Snowflake","optional":true}],"status":"live","first_seen_at":"2026-09-11T10:26:44Z","employer_posted_date":"2026-09-11","last_verified_at":"2026-10-24T20:47:37Z","board_verified":true,"closed_at":null,"days_open":43,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":43},"description":"Leads the design, development, deployment, and maintenance of data and analytics platforms. Develops reliable, scalable, and efficient data pipelines and data processing solutions that enable data to be effectively processed, stored, governed, and made available to analysts and other data consumers. Collaborates with business stakeholders, IT experts, data scientists, architects, and subject-matter experts to deliver enterprise data and analytics solutions aligned with business and technical requirements.\nKey ResponsibilitiesDesign, develop, and automate distributed data ingestion and transformation solutions using data from relational, event-based, semi-structured, and unstructured sources.\nBuild reliable, scalable, and efficient ETL/ELT data pipelines using appropriate tools, technologies, and scripting languages.\nDesign and implement data quality, validation, monitoring, and alerting frameworks to identify and resolve data integrity issues.\nImplement data governance practices covering metadata, data access, retention, compliance, and security.\nDesign and implement physical data models, including database structures, indexing, and table relationships, to support performance and scalability.\nDevelop and operate large-scale data storage and processing solutions across cloud and distributed data platforms, including data lakes, warehouses, and lakehouse environments.\nOptimize data pipelines, Spark workloads, databases, and cloud infrastructure for performance, reliability, scalability, and cost efficiency.\nIntegrate data from a variety of enterprise applications and source systems and support real-time and event-driven data processing.\nDevelop automation for common and repeatable data preparation, integration, deployment, and platform-management activities to minimize manual and error-prone processes.\nImplement CI/CD and DevOps practices to support automated deployment, testing, and release management.\nParticipate in troubleshooting, testing, validation, and continuous improvement of data pipelines and platform solutions.\nEnsure data platforms and solutions meet applicable quality, governance, security, compliance, and regulatory requirements.\nCollaborate with data scientists, analysts, architects, IT teams, and business stakeholders to understand requirements and deliver effective data solutions.\nDocument data solutions, processes, designs, and technical information to support knowledge transfer and operational effectiveness.\nApply Agile development methodologies such as Scrum and Kanban to deliver data engineering initiatives.\nProvide technical leadership and mentor less experienced team members, promoting engineering excellence and collaboration.\n Skills\nStrong technical leadership and decision-making skills, with the ability to lead large-scale data engineering initiatives from concept through production deployment.\nStrong problem-solving and analytical skills, including the ability to diagnose complex data pipeline, platform, and performance issues.\nExcellent communication and collaboration skills, with the ability to work effectively with technical and business stakeholders.\nAbility to translate complex technical concepts and stakeholder requirements into actionable data solutions.\nStrong customer focus and ability to develop solutions aligned with business objectives.\nAbility to balance strategic architecture decisions with hands-on technical execution.\nStrong project management, prioritization, and organizational skills in a fast-paced environment.\nStrong understanding of data quality, governance, security, compliance, and data management principles.\nPassion for continuous improvement, emerging technologies, and modern data engineering practices.\nAbility to mentor, guide, and develop technical talent while fostering a collaborative engineering culture.\nTechnical Skills\nData Engineering & Processing\nAdvanced proficiency in Azure Databricks, Apache Spark, and distributed data processing frameworks.\nStrong expertise in enterprise-scale ETL/ELT and data ingestion pipeline design and development.\nExperience processing structured, semi-structured, streaming, and large-scale datasets.\nStrong understanding of Big Data technologies and scalable cloud-native data architectures.\nProgramming & Development\nAdvanced proficiency in Python and Scala for large-scale data processing and engineering solutions.\nStrong SQL skills for querying, transformation, optimization, and analysis of large datasets.\nExperience with scripting, automation, version control, testing, and build processes.\nCloud & Platform Technologies\nStrong experience with Azure data services, including:Azure Databricks\nAzure Data Lake Storage (ADLS)\nAzure Blob Storage\nAzure Synapse Analytics\nAzure SQL Data Warehouse\n\nStrong understanding of cloud architecture principles, scalability, reliability, and security best practices.\nData Storage & Lakehouse\nExperience with modern data storage and lakehouse technologies, including:Delta Lake\nApache Iceberg\nParquet\nORC\n\nStrong understanding of data lake, data warehouse, and lakehouse architectures.\nStreaming & Data Integration\nExperience with Kafka or similar real-time streaming and event-processing technologies.\nExperience integrating data from a wide variety of enterprise applications and source systems.\nFamiliarity with Qlik Replicate or similar data replication and ingestion technologies is preferred.\nDevOps & Engineering Excellence\nExperience implementing CI/CD pipelines and automated deployment processes.\nStrong knowledge of Git, Jenkins, testing methodologies, version control, and release management.\nExperience establishing coding standards, technical documentation, and engineering governance practices.\nData Quality, Governance & Security\nExperience implementing data validation frameworks, monitoring solutions, and data quality controls.\nKnowledge of cloud security, access management, data governance, compliance, and regulatory requirements.\nExperience designing reliable, auditable, and observable data platforms.\nExperience\n8+ years of hands-on experience in Data Engineering, Data Platform Engineering, Big Data, or a related discipline.\n 3+ years of experience leading technical teams, projects, or significant data engineering initiatives.\nProven experience building and supporting large-scale cloud-based data ingestion, transformation, and analytics platforms.\nExperience developing end-to-end ETL/ELT solutions in Azure cloud environments.\nDemonstrated experience delivering high-performance and scalable distributed data processing solutions using Spark and Databricks.\nExperience optimizing data pipelines, Spark workloads, databases, and cloud infrastructure for performance, reliability, and cost efficiency.\nExperience working with modern data lake, data warehouse, and lakehouse architectures.\nExperience implementing DevOps practices, CI/CD pipelines, and automated deployment processes.\nExperience working within Agile software development methodologies.\nExperience partnering with data scientists, analysts, architects, and business stakeholders to deliver enterprise data solutions.\nExperience analyzing complex business systems, industry requirements, and data regulations.\nExperience processing and managing large datasets.\nExperience designing and developing Big Data platforms using open-source and third-party technologies.\nExperience with technologies such as Spark, Scala/Java, MapReduce, Hive, HBase, and Kafka or equivalent experience.\nExperience developing applications requiring large-scale file movement and data extraction from multiple sources.\nExperience building analytical solutions.\nPreferred / Nice to Have\nExperience with Snowflake and cloud-native data warehousing solutions.\nExperience with Qlik Replicate or similar enterprise data replication technologies.\nExperience supporting real-time analytics and streaming data architectures.\nExperience implementing Infrastructure as Code (IaC) and platform automation frameworks.\nKnowledge of data observability, data lineage, and metadata management tools.\nExperience with IoT technologies.\nExperience supporting AI, machine learning, and advanced analytics workloads on enterprise data platforms.\nExposure to multi-cloud data ecosystems and hybrid cloud architectures.\nAzure Data Engineer Associate, Azure Solutions Architect, or similar cloud certifications.\n Qualifications\nBachelor’s degree or equivalent qualification in Computer Science, Information Technology, Engineering, Data Science, or another relevant technical discipline.\nRelevant equivalent professional experience may be considered.\nRelevant cloud or data engineering certifications are preferred.\nThis position may require licensing or other requirements related to export controls or sanctions regulations.","description_format":"text","description_chars":8774,"description_truncated":false,"requirements":{"experience_years_min":8,"management_years_min":3,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":true},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Industrial Machinery","Automotive Components"],"lifecycle":[{"event":"open","at":"2026-10-23T04:46:22Z"}],"visa":[],"liveness":{"score":12,"band":"cold","label":"Long shot","p_open":1,"p_active":0.438,"p_room":0.28,"age_days":42,"expected_fill_days":15,"reasons":["conf:3","stale_co","wave","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-24T06:02:35Z"},"pay":null,"html_url":"https://alion.io/job/cummins-data-scientist-senior-3","json_url":"https://alion.io/job/cummins-data-scientist-senior-3.json","meta":{"generated_at":"2026-10-25T00:25:49Z","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":651,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-26T00:00:00Z"}},"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":1758413},"rest":"https://alion.io/mcp/rest/get_company?id=1758413"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcummins-data-scientist-senior-3"},{"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%2Fcummins-data-scientist-senior-3"},{"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%2Fcummins-data-scientist-senior-3"},{"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/cummins-data-scientist-senior-3\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcummins-data-scientist-senior-3"}]}