{"id":2618923,"url":"https://alion.io/job/intetics-1155-senior-data-ingestion-engineer","title":"1155 | Senior Data Ingestion Engineer","company":{"id":4245,"name":"Intetics","domain":"intetics.com","url":"https://alion.io/company/intetics","size_band":"501-1000","is_staffing_agency":false,"employer_type":"services","is_intermediary":false,"listed_via":null,"ats_vendor":"Workable","truth_index":{"grade":"C","score":66,"open_postings":104,"ghost_share":0.567,"stale_share":0,"repost_share":0.01,"time_to_fill_p50_days":29,"computed_at":"2026-10-15T05:46:00Z"}},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":null,"work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":["PL","RO","ES","SK","SI"],"hiring_countries_total":5,"salary":null,"salary_estimate":{"min_usd":63000,"max_usd":94000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":72},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon CloudWatch","optional":false},{"name":"Amazon S3","optional":false},{"name":"AWS","optional":false},{"name":"AWS Step Functions","optional":false},{"name":"CI/CD","optional":false},{"name":"Git","optional":false},{"name":"OCR","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"SharePoint","optional":false},{"name":"SQL","optional":false},{"name":"Azure","optional":true},{"name":"Databricks","optional":true},{"name":"SLI/SLO/SLA","optional":true}],"status":"live","first_seen_at":"2026-10-15T12:49:09Z","employer_posted_date":"2026-10-15","last_verified_at":"2026-10-15T20:09:32Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"The Data/Ingestion Engineer will design and implement scalable ingestion pipelines for high-volume structured and unstructured insurance documents, including PDFs, scans, emails, Word, Excel and PowerPoint files.\nThe role includes OCR/document extraction, text cleaning and normalization, semantic chunking, metadata tagging, vector storage/RAG preparation, validation, monitoring and integration with downstream AI solutions.\nRequirements\nAt least 7 years of experience as Data Engineer with Python and SQL\nAt least 5 with AWS, the rest should be more or less but should be real experience that the candidate is able to talk about and give a concrete example/\nMust to have :\nPython\nSQL\nAWS\nS3\nStep Functions\nCloudWatch\nData/document ingestion pipelines\nProcessing of unstructured documents:\nPDF\nscanned documents\nWord\nExcel\nPowerPoint\nemails\nOCR / document extraction technologies\nAWS Textract or equivalent\nConnectors/integrations with sources such as:\nSharePoint\nemail\nText cleaning and normalization\nMetadata extraction/tagging\nAutomated error monitoring\nValidation of OCR/extraction results\nGit\nCI/CD\nTesting\nPublic-cloud data processing/document ingestion experience\nGood to have :\nVector databases\nRAG\nSemantic chunking\nVector-storage schema design\nRetrieval mechanisms\nAzure\nDatabricks\nAWS Textract specifically\nExperience within insurance / financial services\nExperience handling enterprise security and low-latency SLA requirements\nEnglish Level C1\n Duration of the mission : 1 year","description_format":"text","description_chars":1492,"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":[{"language":"English","level":"Advanced (C1)","optional":false}]},"benefits":[],"hiring_locations":[{"name":"Poland","iso":"PL","kind":"country"},{"name":"Romania","iso":"RO","kind":"country"},{"name":"Spain","iso":"ES","kind":"country"},{"name":"Slovakia","iso":"SK","kind":"country"},{"name":"Slovenia","iso":"SI","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Outsourcing & Dedicated Teams","Software Testing & QA","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-10-15T12:49:09Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":29,"reasons":["conf:0","win:early"],"computed_at":"2026-10-15T20:45:55Z"},"pay":null,"html_url":"https://alion.io/job/intetics-1155-senior-data-ingestion-engineer","json_url":"https://alion.io/job/intetics-1155-senior-data-ingestion-engineer.json","meta":{"generated_at":"2026-10-15T20:45:55Z","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":31429,"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":4245},"rest":"https://alion.io/mcp/rest/get_company?id=4245"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fintetics-1155-senior-data-ingestion-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%2Fintetics-1155-senior-data-ingestion-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%2Fintetics-1155-senior-data-ingestion-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/intetics-1155-senior-data-ingestion-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fintetics-1155-senior-data-ingestion-engineer"}]}