What are the responsibilities and job description for the AI / Data Platform Engineer position at WSN?
As an AI-Native Data Platform Engineer, you will design and own the canonical data foundations powering our financial AI systems. This role sits at the core of our platform — building the ontology, data contracts, and reconciliation frameworks that enable intelligent agents to operate safely and autonomously.
AI systems only perform as well as the structure beneath them. You will architect custodial data pipelines, canonical financial models, and AI-ready schemas that support embeddings, retrieval systems, and agent-driven workflows in a regulated wealth management environment.
We are building autonomous agents that reason over and act on platform state — and you will define the data layer that makes that possible.
Your Impact
- Design scalable ingestion pipelines across custodians (Schwab, Fidelity, Pershing, etc.) and internal financial systems
- Build and evolve canonical models for accounts, positions, transactions, balances, corporate actions, and household hierarchies
- Define financial data ontology and enforce strong data contracts across services
- Implement reconciliation frameworks and golden-source resolution across multi-vendor datasets
- Engineer AI-ready data layers optimized for embeddings, vector search, and RAG architectures
- Structure financial datasets to improve prompt reliability and LLM output consistency
- Architect closed-loop, agent-driven systems that monitor, reason over, and autonomously remediate data inconsistencies
- Implement observability, lineage, governance, and fine-grained access controls across regulated datasets
The Ideal Match
- 5 years building production-grade data platforms
- Deep SQL expertise and strong Python for data engineering
- Experience designing canonical schemas and resolving vendor data inconsistencies
- Strong understanding of custodial financial data (positions, trades, balances, performance, corporate actions)
- Familiarity with embeddings, vector databases, and retrieval architectures
- Exposure to prompt engineering and structured context design for LLM systems
- Knowledge of MLOps fundamentals (versioning, monitoring, reproducibility)
- Comfortable with AWS data services (S3, Lambda, ECS, Glue, Redshift, OpenSearch) and event-driven orchestration
- Strong ownership mindset and systems-level thinking
Bonus Points
- Wealth management or capital markets background
- Experience integrating OpenAI or Anthropic APIs into production systems
- Experience designing retrieval schemas for AI agents
- Experience with authorization and policy platforms (e.g., OSO, Auth0)
- Experience implementing fine-grained access control for AI-driven systems
- Familiarity with GitHub-based CI/CD workflows and automation
- Experience with data governance, lineage, and compliance controls