{"id":3444223,"url":"https://alion.io/job/asper-ai-sr-data-engineer","title":"Sr. Data Engineer","company":{"id":8407,"name":"Asper AI","domain":"asper.ai","url":"https://alion.io/company/asper-ai","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":"senior","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":21000,"max_usd":46000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":75},"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Docker","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Git","optional":false},{"name":"GitHub","optional":false},{"name":"Kubeflow","optional":false},{"name":"Machine Learning","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-10-29T06:36:00Z","employer_posted_date":null,"last_verified_at":"2026-10-29T06:36:00Z","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 Senior Data Engineer to design, build, and maintain scalable, high-performance data pipelines that power our SaaS-based AI applications and Predictions-as-a-Service products. The role focuses on building reliable data infrastructure, optimizing data processing workflows, and ensuring data quality to support AI/ML solutions and business decision-making in the Consumer Packaged Goods (CPG) sector. The ideal candidate has strong hands-on experience with Python, PySpark, SQL, Apache Spark, and workflow orchestration tools, along with a proven track record of developing and maintaining production-grade data engineering solutions.\n\nResponsibilities: \nDesign, develop, and maintain scalable ETL/ELT data pipelines for data extraction, ingestion, transformation, and processing.\nBuild, deploy, and orchestrate data workflows using Apache Airflow and/or Kubeflow.\nOwn multiple data pipelines end-to-end, ensuring reliability, scalability, and performance.\nDevelop and maintain production-grade Spark applications using PySpark.\nMonitor, troubleshoot, audit, and optimize existing pipelines to improve data quality, processing speed, and resource utilization.\nImplement real-time pipeline monitoring, alerting, and error-handling mechanisms.\nDesign and maintain efficient data models and scalable big data processing infrastructure.\nFollow modular, configurable, and reusable programming practices using configuration files and parameterized workflows.\nPrepare and maintain High-Level Design (HLD), Low-Level Design (LLD), technical documentation, and implementation plans.\nCollaborate with AI/ML, Machine Learning Engineering (MLE), DevOps, product, and implementation teams to deliver effective data solutions.\nSupport deployed pipelines through bug fixes, enhancements, and ongoing performance improvements.\nContribute to engineering best practices, knowledge sharing, cross-team training, and hiring initiatives.\n\nRequirements: \nStrong programming proficiency in Python, PySpark, and SQL.\nHands-on experience writing, deploying, and maintaining Apache Spark code in production environments.\nProven experience building and supporting scalable ETL/ELT pipelines and data processing workflows.\nExperience with data extraction, ingestion, transformation, monitoring, and alerting.\nFamiliarity with workflow orchestration tools such as Apache Airflow and/or Kubeflow.\nExperience working with public cloud platforms such as AWS or Azure.\nStrong understanding of big data infrastructure, data modeling, and distributed data processing.\nExperience optimizing data loading, ingestion, Spark jobs, and pipeline performance.\nWorking knowledge of developer tools such as Git, GitHub, Docker, and VS Code.\nStrong debugging, problem-solving, and analytical skills.\nAbility to work effectively in a fast-paced, deadline-driven environment and collaborate across multiple teams.\n\nPreferred Candidate Profile: \nStrong ownership of production data pipelines, from development through deployment and maintenance.\nAbility to translate business requirements into scalable, reliable technical solutions.\nGood understanding of software engineering best practices, code quality, and technical documentation.\nExcellent communication and collaboration skills.\nRole Focus: Production Data Engineering, Python, PySpark, SQL, Apache Spark, ETL/ELT, Airflow/Kubeflow, AWS/Azure, Big Data.\nSkills\nApache Spark, Data Pipelines, ELT, ETL, Pipelines, PySpark, Python, Spark","description_format":"text","description_chars":3462,"description_truncated":false,"requirements":{"experience_years_min":2,"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":["Machine Learning","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-10-29T06:36:00Z"}],"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":28,"reasons":["seen:1","velocity","win:early"],"computed_at":"2026-10-31T05:58:55Z"},"pay":null,"html_url":"https://alion.io/job/asper-ai-sr-data-engineer","json_url":"https://alion.io/job/asper-ai-sr-data-engineer.json","meta":{"generated_at":"2026-10-31T09:31:39Z","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":14399,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-01T00:00:00Z"}},"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":8407},"rest":"https://alion.io/mcp/rest/get_company?id=8407"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fasper-ai-sr-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%2Fasper-ai-sr-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%2Fasper-ai-sr-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/asper-ai-sr-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fasper-ai-sr-data-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3444223}},{"tool":"search_jobs","arguments":{"company":"asper.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3444223},"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"}}