{"id":1173154,"url":"https://alion.io/job/recruitment-room-data-engineer","title":"Data Engineer","company":{"id":100174,"name":"Recruitment Room","domain":"recruitmentroom.net","url":"https://alion.io/company/recruitment-room","size_band":null,"is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"inferred_payroll_markers","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":["US"],"hiring_countries_total":1,"salary":{"min":140000,"max":180000,"currency":"USD","period":"year","gross":null,"usd_annual":180000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":true,"technologies":[{"name":"AWS","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Python","optional":false},{"name":"Spark","optional":false},{"name":"SQL","optional":false},{"name":"LLM","optional":true},{"name":"Matplotlib","optional":true},{"name":"Plotly","optional":true},{"name":"Seaborn","optional":true}],"status":"live","first_seen_at":"2026-08-21T07:00:00Z","employer_posted_date":null,"last_verified_at":"2026-08-21T07:00:00Z","board_verified":false,"closed_at":null,"days_open":55,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":55},"description":"Data Engineer\nRemote | Full-time | $140,000-$180,000/year | 1 Opening\nAbout the Role\nBuild and scale the data infrastructure powering AI-driven products and research. Develop distributed data pipelines, manage large-scale datasets across cloud environments, and design reliable systems that support experimentation and model development at scale.\nKey Responsibilities\nDesign, build, and maintain scalable data pipelines for ingestion, processing, and transformation\n\nDevelop distributed workflows using Spark and cloud-native technologies\n\nBuild and maintain SQL/NoSQL storage solutions for performance and reliability\n\nArchitect AWS-based systems for high-volume data ingestion and distribution\n\nWrite efficient Python and SQL code for ETL and analysis\n\nEnsure data quality, integrity, monitoring, and operational reliability\n\nCollaborate with AI researchers, data scientists, and engineers on data-intensive applications\n\nImplement automation, orchestration, and monitoring workflows for scalable operations\n\nRequired Skills\nPython\n\nSQL\n\nAI/ML\n\nSpark\n\nAWS\n\nQualifications\nStrong proficiency in Python, SQL, and distributed frameworks (Apache Spark)\n\nHands-on experience with AWS data services and cloud-native architectures\n\nExperience with SQL and NoSQL databases\n\nProven ability to manage and process large-scale datasets in distributed environments\n\nUnderstanding of data partitioning, performance optimization, and scalable architectures\n\nNice to Have\nExposure to AI/ML workflows or research environments\n\nExperience with visualization tools (Matplotlib, Seaborn, Plotly)\n\nFamiliarity with LLM-related data workflows (training, evaluation, prompt experimentation)\n\nCompensation & Benefits\nPay range: $140,000-$180,000/year\n\nEquity compensation eligibility\n\nPerformance-based bonuses\n\nComprehensive benefits package including:\nUp to 100% reimbursement for health-insurance premiums\n\nPaid time off\n\n401(K) plan with company match\n\nAdditional benefits supporting a high-performing, remote-first workforce\n\nEqual Opportunity\nAll qualified applicants will receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, genetic information, veteran status, or any other characteristic protected by law.","description_format":"text","description_chars":2278,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Equity"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-09-24T09:13:47Z"}],"visa":[],"liveness":{"score":3,"band":"cold","label":"Long shot","p_open":0.4,"p_active":0.298,"p_room":0.28,"age_days":54,"expected_fill_days":27,"reasons":["seen:54","agency","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-15T05:46:00Z"},"pay":{"stated_usd_annual":180000,"is_top_pay":true},"html_url":"https://alion.io/job/recruitment-room-data-engineer","json_url":"https://alion.io/job/recruitment-room-data-engineer.json","meta":{"generated_at":"2026-10-15T15:24:18Z","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":23570,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-16T00:00:00Z"}},"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":100174},"rest":"https://alion.io/mcp/rest/get_company?id=100174"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Frecruitment-room-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%2Frecruitment-room-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%2Frecruitment-room-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/recruitment-room-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Frecruitment-room-data-engineer"}]}