{"id":3580002,"url":"https://alion.io/job/raydar-data-engineer-2","title":"Data Engineer","company":{"id":4478753,"name":"Raydar","domain":"raydar.com","url":"https://alion.io/company/raydar-com","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workable","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":"board_field","remote_working_hours":{"label":"ET","utc_offset_min":-5,"utc_offset_max":-5},"hiring_geo_confidence":"structured","locations":[],"countries":[],"hiring_countries":["US"],"hiring_countries_total":1,"salary":{"min":180000,"max":220000,"currency":"USD","period":"year","gross":null,"usd_annual":220000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon S3","optional":false},{"name":"AWS","optional":false},{"name":"LLM","optional":false},{"name":"OCR","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Semantic Search","optional":false},{"name":"SQL","optional":false},{"name":"Pinecone","optional":true}],"status":"live","first_seen_at":"2026-09-30T00:00:00Z","employer_posted_date":"2026-09-30","last_verified_at":"2026-11-02T05:11:27Z","board_verified":true,"closed_at":null,"days_open":33,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":33},"description":"About the company\nOur client builds AI-powered legal software for research and litigation workflows. Its products use large collections of court records and legal documents to help turn complex information into structured insights.\nThe role / why it matters\nYou will own the data pipelines that ingest, normalize, and enrich caselaw and docket records. Legal source data is messy, often arriving as scanned filings or semi-structured documents. The reliable signal you create will support downstream research and AI products.\nWhat you'll do\nBuild and maintain production pipelines for PACER, NYSCEF, state court systems, published opinions, and other legal records.\nTurn PDFs, scanned filings, XML, and HTML into clean, queryable data.\nCreate LLM-assisted extraction workflows for legal text and validate results against source documents.\nRun statistical analyses, improve data quality, and optimize SQL queries.\nSupport RAG and semantic search workflows in partnership with full-stack engineers.\nOperate and improve AWS S3 and RDS data systems within established security and compliance guardrails.\nWhat we're looking for\n4-8 years of experience building and operating production data pipelines with large, dirty datasets, and quickly finding signal in them.\nStrong Python and SQL skills for pipeline engineering and data analysis.\nHands-on experience with legal data such as PACER records, court dockets, or court filings.\nExperience with AI for data, including RAG, semantic search, and LLM-assisted extraction, plus PDF parsing, OCR, and document extraction tooling.\nA bachelor's degree in Computer Science, Data Science, or a related field.\nWorks fully autonomously and thrives with minimal management direction; stays curious about messy data problems and critically reviews AI-assisted code and outputs.\nBonus points\nExperience with regulatory or government data sources.\nExperience with vector databases or semantic-search tooling such as Pinecone or Voyage AI.\nCompensation and benefits\nBase salary: $180,000-$220,000 USD.\nEquity: 0.15%-0.25%.\nLocation / work model\nRemote within the United States, with at least four hours of overlap with Eastern Time each workday.\nStrong preference for candidates based in the New York City area.\nPlan for quarterly travel to New York City.\nVisa transfers may be considered. New visa sponsorship is not available.","description_format":"text","description_chars":2358,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"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":"2026-11-01T01:38:31Z"}],"visa":[],"liveness":{"score":25,"band":"fade","label":"Fading","p_open":1,"p_active":0.556,"p_room":0.45,"age_days":33,"expected_fill_days":17,"reasons":["conf:1","velocity","win:tail","comp:brand"],"computed_at":"2026-11-02T06:13:15Z"},"pay":{"stated_usd_annual":220000,"is_top_pay":true},"html_url":"https://alion.io/job/raydar-data-engineer-2","json_url":"https://alion.io/job/raydar-data-engineer-2.json","meta":{"generated_at":"2026-11-02T09:09:08Z","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":12747,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-03T00:00:00Z"}},"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":4478753},"rest":"https://alion.io/mcp/rest/get_company?id=4478753"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fraydar-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%2Fraydar-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%2Fraydar-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/raydar-data-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fraydar-data-engineer-2"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3580002}},{"tool":"search_jobs","arguments":{"company":"raydar.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3580002},"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"}}