{"id":3530426,"url":"https://alion.io/job/cml-team-data-engineer","title":"Data Engineer","company":{"id":4486111,"name":"CML Team","domain":"cmlteam.com","url":"https://alion.io/company/cml-team","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":"middle","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Ukraine"],"countries":["UA"],"hiring_countries":["UA"],"hiring_countries_total":1,"salary":null,"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Airflow","optional":false},{"name":"Amazon Redshift","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Dagster","optional":false},{"name":"Databricks","optional":false},{"name":"dbt","optional":false},{"name":"Docker","optional":false},{"name":"ETL/ELT","optional":false},{"name":"GCP","optional":false},{"name":"Git","optional":false},{"name":"Google BigQuery","optional":false},{"name":"Prefect","optional":false},{"name":"Python","optional":false},{"name":"Snowflake","optional":false},{"name":"SQL","optional":false},{"name":"Amazon Kinesis","optional":true},{"name":"Apache Kafka","optional":true},{"name":"Embeddings","optional":true},{"name":"Fivetran","optional":true},{"name":"LLM","optional":true},{"name":"Looker","optional":true},{"name":"Power BI","optional":true},{"name":"pySpark","optional":true},{"name":"RAG","optional":true},{"name":"Spark","optional":true},{"name":"Terraform","optional":true}],"status":"live","first_seen_at":"2026-10-30T15:17:12Z","employer_posted_date":null,"last_verified_at":"2026-10-30T15:17:12Z","board_verified":false,"closed_at":null,"days_open":4,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":4},"description":"We're seeking a talented Data Engineer to design and build reliable data pipelines and warehouses for data-heavy products serving clients in the US and Europe. If you're experienced with Python, SQL, modern data warehouses, and orchestration tools and enjoy turning complex datasets into valuable business insights, we'd love to hear from you!\n\nCore Competence:\n\nAt least 3 years of professional experience in Data Engineering, with strong Python and SQL skills, including window functions and query performance optimization.\n\nProduction experience with modern data warehouses such as Snowflake or BigQuery. Experience with Redshift or Databricks is also relevant.\n\nHands-on experience with dbt in production projects, including data models, tests, sources, and incremental materializations.\n\nPractical experience with Apache Airflow or similar orchestration tools such as Dagster or Prefect.\n\nStrong understanding of ETL / ELT architecture, including incremental loads, change data capture, slowly changing dimensions, and idempotent pipeline execution.\n\nExperience building and maintaining batch and incremental data pipelines integrating APIs, databases, files, and SaaS platforms.\n\nProficiency with Git, Docker, and at least one major cloud platform such as AWS, GCP, or Azure.\n\nPreferred Qualifications:\n\nExperience with Apache Spark, PySpark, or Databricks.\n\nKnowledge of streaming technologies such as Kafka, Kinesis, or Pub/Sub.\n\nFamiliarity with Fivetran, Airbyte, or Terraform for data infrastructure.\n\nExperience with BI tools such as Power BI, Looker, or QuickSight and data modeling for analytics.\n\nExperience preparing datasets for LLM and RAG applications, including chunking, embeddings, and vector databases.\n\nUpper-intermediate level of English for clear and effective communication with international clients.\n\nWhat We Offer You:\n\nCompetitive compensation aligned with your skills, experience, and career ambitions.\n\nAn innovative work environment with opportunities to build production data platforms, scalable pipelines, and analytics solutions for international clients.\n\nDirect communication with clients from the US and Europe and the opportunity to influence data architecture and technical decisions.\n\nLong-term cooperation with opportunities to move between projects and continue growing with the team.","description_format":"text","description_chars":2329,"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":[{"name":"Ukraine","iso":"UA","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Blockchain & Crypto","Machine Learning"],"lifecycle":[{"event":"open","at":"2026-10-30T15:41:15Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":3,"expected_fill_days":27,"reasons":["seen:3","velocity","win:early"],"computed_at":"2026-11-03T05:54:40Z"},"pay":null,"html_url":"https://alion.io/job/cml-team-data-engineer","json_url":"https://alion.io/job/cml-team-data-engineer.json","meta":{"generated_at":"2026-11-03T23:59:53Z","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":2299,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-04T00:00:00Z"}},"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":4486111},"rest":"https://alion.io/mcp/rest/get_company?id=4486111"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcml-team-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%2Fcml-team-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%2Fcml-team-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/cml-team-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcml-team-data-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3530426}},{"tool":"search_jobs","arguments":{"company":"cmlteam.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3530426},"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"}}