Data Engineer | Data Scientist
Core
Build a private, access-scoped context layer over a private investment group's unstructured data (transcripts, emails, chats, documents) to enable AI skills and agents.
Role type
Senior Data Engineer (Unstructured Data & AI Infrastructure)
Builds
A context layer with ingestion pipelines, vector/graph stores, and identity-resolved data for an AI/LLM system.
Domain
Financial Services / Unstructured Data Engineering / AI Infrastructure
Deliverable
production ML models
Required skills
Python, SQL, Unstructured data pipelines, Entity resolution, Vector stores, Orchestration (Airflow/Step Functions), API integration, AWS/GCP, PII handling
Preferred skills
RAG architecture, Financial services security practices, LLM upstream choices
Technologies
Python, SQL, Airflow, Step Functions, pgvector, OpenSearch, Pinecone, AWS, GCP, Google Workspace, M365, Slack
Responsibilities
Stand up capture for calls, email, Slack, and messengers; Backfill historical archives; Build document parsing for PDFs and scanned files; Implement identity and entity resolution; Build chunking and embedding pipelines; Implement incremental sync; Attach access scope and provenance; Run PII detection and redaction; Orchestrate pipelines with alerting; Manage cost and latency at scale.
Seniority
Senior, hands-on IC