{"id":2905591,"url":"https://alion.io/job/pgd-senior-ai-data-engineer","title":"Senior AI Data Engineer","company":{"id":4319528,"name":"PGD","domain":"pgd.rs","url":"https://alion.io/company/pgd-rs","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":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":21000,"max_usd":46000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":75},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Azure","optional":false},{"name":"Azure Data Factory","optional":false},{"name":"Embeddings","optional":false},{"name":"GDPR","optional":false},{"name":"LLM","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"SharePoint","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-10-13T05:10:07Z","employer_posted_date":null,"last_verified_at":"2026-10-13T05:10:07Z","board_verified":false,"closed_at":null,"days_open":17,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":17},"description":"Global Growth – Global BD Agent Suite:\nBuild the permission-aware knowledge layer under the Global BD agents. Ingest and keep fresh the Global BD Hub, SharePoint, Salesforce and licensed sources; extract, chunk and PII-scrub content; carry access-control metadata to the search index; and make sure agents only ever retrieve what the requesting user is entitled to see.\n\nMandatory focus:\nMicrosoft Graph delta queries and change webhooks; Salesforce CDC / SOQL / Bulk API; Azure Data Factory / Logic Apps and Azure Functions; ADLS Gen2; Azure AI Search indexing with ACL metadata; document extraction and PII scrubbing.\n\nKey Responsibilities:\nBuild ingestion from SharePoint Online / Global BD Hub using Graph delta queries and change webhooks, and from Salesforce using CDC and SOQL watermark pulls.\nLand data in an immutable, source-first, date-partitioned ADLS Gen2 raw zone and maintain lineage.\nExtract and chunk PDF, Word, Excel and PowerPoint content, preserving tables, headings and metadata for retrieval.\nPropagate permissions by carrying SharePoint / Salesforce ACLs into chunk metadata so Azure AI Search can security-trim results per user.\nScrub PII in pitch records, client bios and contact data in line with GDPR and Purview classification.\nOnboard licensed sources such as COMvergence and other third-party data, validating API availability, licensing and usage constraints with source owners.\nMonitor freshness quality and failures, and flag stale, duplicate or contradictory content back to the Hub team.\n\nRequired Skills & Expected Capability:\nCore Data Engineering: Strong Python and SQL; pipeline orchestration with Azure Data Factory/Logic Apps; Azure Functions\nM365 / SharePoint Data: Microsoft Graph API, delta queries, change notifications / webhooks, SharePoint lists, libraries and permissions model\nSalesforce Data: Salesforce CDC, SOQL, Bulk API, Platform Events\nSearch Indexing: Azure AI Search indexes, indexers and skillsets; embeddings pipelines; hybrid (vector + metadata) retrieval support\nGovernance: ACL propagation, PII detection and scrubbing, Purview, data lineage, GDPR awareness\n\nYou will fit right in if you have:\n5–8 years in data engineering, with 1+ year preparing unstructured content for RAG / LLM use\nHas built ingestion from SharePoint / M365 and / or Salesforce in an enterprise tenant\nUnderstands that a wrong permission on a chunk is a data-exposure incident, not a bug","description_format":"text","description_chars":2422,"description_truncated":false,"requirements":{"experience_years_min":5,"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":[],"lifecycle":[{"event":"open","at":"2026-10-20T07:12:25Z"}],"visa":[],"liveness":{"score":61,"band":"ok","label":"Likely open","p_open":0.85,"p_active":0.795,"p_room":0.9,"age_days":17,"expected_fill_days":28,"reasons":["seen:17","win:mid"],"computed_at":"2026-10-30T05:48:23Z"},"pay":null,"html_url":"https://alion.io/job/pgd-senior-ai-data-engineer","json_url":"https://alion.io/job/pgd-senior-ai-data-engineer.json","meta":{"generated_at":"2026-10-30T14:47:24Z","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":2306,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-31T00:00:00Z"}},"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":4319528},"rest":"https://alion.io/mcp/rest/get_company?id=4319528"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fpgd-senior-ai-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%2Fpgd-senior-ai-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%2Fpgd-senior-ai-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/pgd-senior-ai-data-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fpgd-senior-ai-data-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":2905591}},{"tool":"search_jobs","arguments":{"company":"pgd.rs","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":2905591},"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"}}