AI Data Engineer (Contractor) — Consello (via Remotesome)

About Consello

Consello is a New York-based advisory and investing platform serving CEOs, boards, and leadership teams across investor relations, M&A advisory, consulting, executive search, private equity, and digital assets. The firm is building a secure AI platform for its advisors on Microsoft Azure.

About Consello

Consello is a New York-based advisory and investing platform serving CEOs, boards, and leadership teams across investor relations, M&A advisory, consulting, executive search, private equity, and digital assets. The firm is building a secure AI platform for its advisors on Microsoft Azure.

Engagement Details

• Type: Direct contractor, full-time equivalent commitment
• Location: Remote with substantial U.S. Eastern Time overlap
• Reporting: Consello AI Lead, working within a small senior product/engineering team
• Duration: Initial 3-month term, extension expected
• Security: All work performed inside Consello’s Azure tenant

Required Experience & Tech Stack

• Data engineering (5+ years): Production Python and strong SQL; designing schemas, pipelines, and incremental/CDC-style sync at scale; data modeling for both analytical and operational retrieval
• Knowledge representation: Designing ontologies and entity/edge schemas for real domains — property-graph vs. RDF/triple-store trade-offs, taxonomy design, provenance and confidence modeling, schema evolution over time
• Graph-based systems: Hands-on production experience with a graph database — Neo4j/Cypher, Azure Cosmos DB (Gremlin), TigerGraph, or equivalent
• Entity resolution: Identity stitching across messy heterogeneous sources — deterministic and probabilistic matching, dedup, alias handling, human-review loops
• Microsoft Graph data: Ingesting mail/calendar/files/chat metadata via Microsoft Graph API — auth models (app-only vs. delegated), throttling, delta sync, webhooks, and permission-aware handling
• Azure data stack: Azure SQL, Blob Storage, Azure Functions, Azure AI Search (vector/hybrid indexes, indexers, security trimming); Entra ID managed-identity auth patterns
• AI retrieval & memory: Production RAG systems — embedding model selection, chunking strategies, hybrid search and reranking, evaluation of retrieval quality
• Architecture ownership: Track record of owning platform-level decisions, writing design docs, and defending trade-offs
• Engineering hygiene: Git/GitHub, CI/CD (GitHub Actions), infrastructure-as-code (Bicep or Terraform), secure secret/identity handling

Nice to Have

• GraphRAG or knowledge-graph-augmented LLM retrieval in production
• Microsoft Fabric, Databricks, or Synapse; streaming (Event Grid / Event Hubs / Kafka)
• CRM data models (Salesforce/Dynamics); third-party relationship or market data integration
• Financial services data domain; compliance-aware data governance
• MCP (Model Context Protocol) for exposing data services to AI agents; AI-assisted development (Claude Code or similar)

Required Skills

• Python — MORE_THAN_2_YEARS_PROFESSIONALLY
• SQL — MORE_THAN_2_YEARS_PROFESSIONALLY
• Neo4j — MORE_THAN_2_YEARS_PROFESSIONALLY
• Azure AI Search — MORE_THAN_2_YEARS_PROFESSIONALLY
• Azure SQL — MORE_THAN_2_YEARS_PROFESSIONALLY
• Azure Functions — MORE_THAN_2_YEARS_PROFESSIONALLY
• RAG — MORE_THAN_2_YEARS_PROFESSIONALLY
• Microsoft Graph API — MORE_THAN_2_YEARS_PROFESSIONALLY
• Entity Resolution — MORE_THAN_2_YEARS_PROFESSIONALLY

Benefits

• Fully Remote

Compensation

$120K – $140K/year

Timezone: UTC-8 to UTC+0