3 months ago
Responsibilities
- Design scalable ingestion pipelines across custodians and internal financial systems.
- Build and evolve canonical models for financial data.
- Define financial data ontology and enforce data contracts across services.
- Implement reconciliation frameworks and resolve multi-vendor dataset inconsistencies.
- Engineer AI-ready data layers optimized for embeddings and vector search.
- Structure financial datasets to enhance prompt reliability and LLM output consistency.
- Architect closed-loop systems for monitoring and remediating data inconsistencies.
- Implement observability, lineage, governance, and access controls for regulated datasets.
Requirements
- 5+ years of experience building production-grade data platforms.
- Deep SQL expertise and strong Python skills for data engineering.
- Experience designing canonical schemas and resolving vendor data inconsistencies.
- Strong understanding of custodial financial data.
- Familiarity with embeddings, vector databases, and retrieval architectures.
- Exposure to prompt engineering for LLM systems.
- Knowledge of MLOps fundamentals.
- Comfortable with AWS data services and event-driven orchestration.
- Strong ownership mindset and systems-level thinking.
Benefits
- Learn and grow through book clubs, seminars, and peer learning sessions.
- Full health benefits plus 401(k) matching and Roth IRA options.
- Unlimited PTO.
- Collaborative atmosphere between product, design, and engineering.