{"id":2999724,"url":"https://alion.io/job/klimb-io-data-engineer-2","title":"Data Engineer","company":{"id":1318,"name":"Klimb.io","domain":"klimb.io","url":"https://alion.io/company/klimb-io","size_band":"1001-5000","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":"middle","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Mumbai, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":14000,"max_usd":36000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":21},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"Amazon Kinesis","optional":false},{"name":"Amazon Redshift","optional":false},{"name":"Amazon S3","optional":false},{"name":"Apache Kafka","optional":false},{"name":"AWS","optional":false},{"name":"AWS Lambda","optional":false},{"name":"AWS Step Functions","optional":false},{"name":"CI/CD","optional":false},{"name":"Dimensional Modeling","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Flink","optional":false},{"name":"Git","optional":false},{"name":"IAM","optional":false},{"name":"Linux","optional":false},{"name":"pySpark","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"Unix","optional":false},{"name":"Amazon ECS","optional":true},{"name":"Amazon EKS","optional":true},{"name":"Apache Hudi","optional":true},{"name":"Apache Iceberg","optional":true},{"name":"Databricks","optional":true},{"name":"Delta Lake","optional":true},{"name":"Docker","optional":true},{"name":"Kubernetes","optional":true}],"status":"live","first_seen_at":"2026-10-21T11:35:15Z","employer_posted_date":null,"last_verified_at":"2026-10-21T11:35:15Z","board_verified":false,"closed_at":null,"days_open":3,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":3},"description":"We're seeking a Data Engineer with 3-4 years of experience to join our growing tech team. The ideal candidate will have hands-on experience in building and managing scalable data systemson AWS, with strong expertise in data pipelines, real-time streaming, and modern data frameworks in building and managing scalable data systems on AWS using Spark and modern data frameworks.\n\nResponsibilities: \nDesign, build, and maintain end-to-end data pipelines for ingestion, transformation, and delivery of high-volume data.\nDevelop Spark-based ETL/ELT workflows for both batch and real-time streaming data.\nCore Skills: Spark, AWS (S3 Glue, Redshift, Kinesis), Kafka, Airflow, Python, SQL.\nIntegrate data from multiple internal and external systems using Kafka, Kinesis, or other streaming frameworks.\nBuild and manage data models, warehouses, and lakehouses using AWS services such as S3 Glue, Redshift, Athena, etc.\nImplement data quality checks, validation rules, and monitoring to ensure reliability and consistency.\nCollaborate with data analysts and scientists to provide clean, structured datasets optimised for analytics and ML.\nWork with orchestration tools (Airflow, MWAA, Step Functions, etc. ) for automated workflow scheduling.\nContinuously optimise data pipelines for cost, scalability, and performance.\n\nRequirements: \nStrong programming skills in Python for data manipulation and automation.\nHands-on expertise in Apache Spark (PySpark or Spark SQL) for large-scale data processing.\nDeep understanding of the AWS data ecosystem: S3 Glue, Lambda, Redshift, Athena, EMR, Kinesis, IAM.\nExperience with real-time streaming platforms such as Kafka, Kinesis, or Flink.\nStrong command of SQL and data modelling (star schema, dimensional modelling, partitioning).\nProficiency with data orchestration and workflow management tools (Airflow, Step Functions, etc. ).\nFamiliarity with Git, CI/CD, and modern development best practices.\nExperience working in Linux/Unix environments and handling large datasets efficiently.\n\nGood to Have: \nExposure to data lakehouse technologies (Delta Lake, Iceberg, Hudi).\nUnderstanding of data governance, cataloguing, and lineage tools (Glue Data Catalogue, Amundsen, DataHub).\nFamiliarity with containerization and deployment (Docker, ECS, EKS).\nBasic understanding of AI/ML.\nBachelor's degree in Computer Science, IT, Engineering, or related technical field.\n3-4 years of experience in data engineering, big data, or analytics infrastructure.\nSkills\nApache Spark, Data Lake, Data bricks, Data engineer, Data warehouse, Data warehousing, Databricks, Datalake, Date engineering, ELT, ETL, Pipeline, PySpark, Python, Spark, Spark SQL, data pipeline, data pipelines, data processing","description_format":"text","description_chars":2713,"description_truncated":false,"requirements":{"experience_years_min":3,"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":["Recruiting Software & ATS"],"lifecycle":[{"event":"open","at":"2026-10-21T11:35:15Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":2,"expected_fill_days":23,"reasons":["seen:2","velocity","win:early"],"computed_at":"2026-10-24T06:02:35Z"},"pay":null,"html_url":"https://alion.io/job/klimb-io-data-engineer-2","json_url":"https://alion.io/job/klimb-io-data-engineer-2.json","meta":{"generated_at":"2026-10-25T04:25:40Z","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":5859,"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":1318},"rest":"https://alion.io/mcp/rest/get_company?id=1318"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fklimb-io-data-engineer-2"},{"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%2Fklimb-io-data-engineer-2"},{"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%2Fklimb-io-data-engineer-2"},{"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/klimb-io-data-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fklimb-io-data-engineer-2"}]}