{"id":874038,"url":"https://alion.io/job/ksb-senior-engineer-data-engineering","title":"Senior Engineer - Data Engineering","company":{"id":712788,"name":"KSB","domain":"ksb.com","url":"https://alion.io/company/ksb-4","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"C","score":67,"open_postings":203,"ghost_share":0.557,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":28,"computed_at":"2026-10-03T05:45:00Z"}},"role":"Data Science","role_family":"Data Science","seniority":"senior","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":null,"salary_estimate":{"min_usd":21000,"max_usd":43000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":51},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Apache Kafka","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"Databricks","optional":false},{"name":"Git","optional":false},{"name":"GitLab CI","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-06-02T00:00:00Z","employer_posted_date":"2026-06-02","last_verified_at":"2026-10-04T02:14:44Z","board_verified":true,"closed_at":null,"days_open":124,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":123},"description":"Key Responsibilities\nContribute to the design and development of scalable data pipelines and a growing data lake\nBuild and extend data processing workflows using Python, Apache Spark, and Databricks\nDefine technical standards, best practices, and reusable frameworks for data engineering\nEnsure data quality, reliability, performance, and maintainability across data solutions\nSupport data modeling, data integration, and transformation processes for analytics and reporting\nDrive automation, monitoring, and CI/CD improvements to ensure operational excellence\nCollaborate across teams, acting as a technical interface between the data platform and engineering, analytics, and business stakeholders.\nContribute to architecture decisions and long-term data platform strategy\nYour Profile\nOutstanding programming experience, preferably in Python; ability to write clean, testable, production-grade code; able to write clean, testable, production-grade code\nStrong SQL skills and familiarity with structured and semi-structured data formats (JSON, Protobuf, Delta format)\nHands-on experience with Apache Spark, ideally on Databricks, and understanding of the medallion architecture\nSolid grasp of data lakehouse principles, data modeling, and data governance concepts\nExperience building and maintaining CI/CD pipelines (e.g. GitLab CI); familiarity with IaC and deployment\nCloud Platforms: Experience with AWS or comparable cloud providers; familiarity with Databricks as a managed Lakehouse platform\nExperience with event-driven architectures or streaming platforms (e.g. Kafka)\nProven track record deploying, monitoring, and maintaining data pipelines and services in production environments; experience with testing practices \nAble to work autonomously and take ownership of tasks end-to-end\nClear and concise communicator - comfortable working across engineering and data teams\nEducation & experieance\nBachelor's degree in Software Engineering, Mathematics, Physics, or a related field\n3 years of project/coding experience in a company\nCloud experience:Databricks, AWS/Azure\nStaging, testing, Git, pipelines\nDistributed systems, data pipelines\n\nPython experience:Versioning, package management, requirements/environments\nChange data capture\n\nData engineering experience:SQL\nPartitioning\nData structures (tables, relations)\nLakehouse","description_format":"text","description_chars":2334,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Science & Engineering","Chemical Engineering"],"lifecycle":[{"event":"open","at":"2026-09-13T18:59:32Z"}],"visa":[],"liveness":{"score":8,"band":"cold","label":"Long shot","p_open":1,"p_active":0.293,"p_room":0.28,"age_days":123,"expected_fill_days":28,"reasons":["conf:1","stale_co","velocity","ghost","win:tail","crowd:brand"],"computed_at":"2026-10-03T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/ksb-senior-engineer-data-engineering","json_url":"https://alion.io/job/ksb-senior-engineer-data-engineering.json","meta":{"generated_at":"2026-10-04T02:16:42Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":3192,"day_limit":5000,"remaining_today":1808,"minute_limit":60,"resets_at":"2026-10-05T00:00:00Z"}}}