{"id":155585,"url":"https://alion.io/job/viaduct-data-engineer","title":"Data Engineer","company":{"id":8444,"name":"Viaduct","domain":"viaduct.ai","url":"https://alion.io/company/viaduct","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","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":["Ljubljana, Slovenia","Slovenia"],"countries":["SI"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":31000,"max_usd":84000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":865},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agile","optional":false},{"name":"Airflow","optional":false},{"name":"Amazon S3","optional":false},{"name":"Apache Hudi","optional":false},{"name":"Apache Kafka","optional":false},{"name":"C++","optional":false},{"name":"Delta Lake","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Java","optional":false},{"name":"Kubernetes","optional":false},{"name":"Machine Learning","optional":false},{"name":"Prefect","optional":false},{"name":"Python","optional":false},{"name":"Scala","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-05-19T11:55:31Z","employer_posted_date":"2026-06-03","last_verified_at":"2026-10-16T12:28:51Z","board_verified":true,"closed_at":null,"days_open":150,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":149},"description":"Who We Are\nWe are a diverse and focused team motivated to solve the hardest problems in the automotive industry through machine learning. We have developed an end-to-end machine learning platform to empower automakers to build safer, smarter, and personalized vehicles. Our platform increases connected vehicle data accessibility and actionability for automakers, their partners and their end-customers.\nWho You Are\nYou are a thoughtful engineer. You understand the complexities of distributed systems and how to triage and solve issues that arise with them. Scalability is top of mind when designing any system or writing code. You believe building a better ETL system requires close collaboration with the machine learning and data science teams.\nAbout the Role\nAs an early data engineer at Viaduct, an analytics and ML platform company, your work is critical to our success. You are responsible for ensuring data quality and reliability in every part of our ETL pipeline, from ingestion to client integrations. \nResponsibilities\nCreating and supporting batch, incremental, and real-time ETL pipelines\nStandardizing ingestion, validation, and cleaning processes across clients\nAutomating data validation to increase data quality\nManaging and evolving schemas in all parts of our pipeline\nMonitoring, tuning, and optimizing Spark jobs\nBecoming a domain-expert in connected vehicle data\nAbout You\n3+ years as a data engineer\nExperience as a tech lead or mentor\nProficiency in Python/Scala/Java/C++ and SQL\n3+ years of experience with Spark or equivalent technologies\n2+ years of experience with a workflow scheduler (Airflow, Prefect, Argo, etc) \n2+ years of experience with distributed file-systems (HDFS, S3, etc)\nFamiliar with the tools in open-source data ecosystem (Apache, CNCF, etc)\nExperience with incremental or real-time processing (Delta Lake, Apache Hudi, Kafka Stream, Spark Streaming, etc) \nSecurity and Privacy Responsibilities\nFollow our policy and procedure documents related to security and privacy\nFollow the security and privacy guidelines in the Employee Handbook\nParticipate in new hire and annual training for security and privacy\nTreat data security and privacy as one of your primary job responsibilities\nReport Security Incidents you discover as bugs\nGet approval from the Security Team before adding new 3rd party software to our codebase\nExplicitly consider security implications when doing PR reviews\nBonus\nExperience with Kubernetes\nExperience working with ML teams\nContributor to open source projects\nExperience in the Automotive industry or a love of cars\nPrior work in small, agile teams","description_format":"text","description_chars":2620,"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":["Predictive Analytics","Industrial AI"],"lifecycle":[{"event":"open","at":"2026-05-19T11:55:31Z"}],"visa":[],"liveness":{"score":9,"band":"cold","label":"Long shot","p_open":1,"p_active":0.314,"p_room":0.28,"age_days":149,"expected_fill_days":32,"reasons":["conf:2","win:tail","crowd:"],"computed_at":"2026-10-16T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/viaduct-data-engineer","json_url":"https://alion.io/job/viaduct-data-engineer.json","meta":{"generated_at":"2026-10-16T15:14:31Z","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":15039,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-17T00:00:00Z"}},"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":8444},"rest":"https://alion.io/mcp/rest/get_company?id=8444"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fviaduct-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%2Fviaduct-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%2Fviaduct-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/viaduct-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fviaduct-data-engineer"}]}