AI-Native FinTech Data Platform Architect

Farther; York and North Yorkshire; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Opportunity to work with a talented 팀

Venture-backed growth

Job summary

Farther seeks an AI-Native Data Platform Engineer to design and own the canonical data foundations powering our financial AI systems. You will architect custodial data pipelines, canonical models, and AI-ready schemas for embeddings, retrieval, and agent-driven workflows in a regulated wealth-management environment.

You will build scalable ingestion across custodians, implement reconciliation, data contracts, governance, and observability to ensure data quality and prompt reliability for LLMs

Qualifications

• 5+ years building production-grade data platforms.
• Exposure to prompt engineering and structured context design for LLM systems.
• Familiarity with embeddings, vector databases, and retrieval architectures.

Responsibilities

• Design scalable ingestion pipelines across custodians and internal systems.
• Define financial data ontology and enforce data contracts across services.
• Implement reconciliation frameworks and golden-source resolution across multi-vendor datasets.
• Engineer AI-ready data layers for embeddings, vector search, and RAG architectures.

Skills

5+ years experience

prompt engineering

embeddings

vector databases

retrieval architectures

AWS data services

SQL

Python

canonical schemas

MLOps

data governance

access control

wealth management

OpenAI integration

Anthropic integration

GitHub CI/CD

Tools

OpenAI API

Anthropic API

GitHub Actions

OSO

Auth0

OpenSearch

AWS S3

Lambda

Job description

Farther seeks an AI-Native Data Platform Engineer to design and own the canonical data foundations powering our financial AI systems. You will architect custodial data pipelines, canonical models, and AI-ready schemas for embeddings, retrieval, and agent-driven workflows in a regulated wealth-management environment.

You will build scalable ingestion across custodians, implement reconciliation, data contracts, governance, and observability to ensure data quality and prompt reliability for LLMs