Polaryx Technologies is a DeepTech Company focused on AI-driven Research, Analysis, and Decision Intelligence for next-gen active asset managers. They are seeking a Senior Data Engineer to architect systems that power automated research agents by building scalable data pipelines and designing ontology-driven architecture.
Responsibilities:
- Design and implement the backend structures that represent complex financial relationships (e.g., mapping management commentary to specific KPIs or industry benchmarks)
- Replace legacy, siloed data handling with robust pipelines that ingest, clean, and structure data from SEC filings, earnings transcripts, and alternative feeds in real-time
- Build the backend environment where our agents operate, enabling them to 'observe' analyst workflows, access evidence packs, and refine their models based on feedback
- Engineer low-latency retrieval systems that allow PMs to query vast amounts of narrative data instantly, moving beyond simple keyword search to semantic understanding
Requirements:
- 8+ years of experience building distributed systems in Python or Java
- Experience working with financial datasets (market data, fundamental data, corporate actions)
- Experience building systems that handle unstructured text (transcripts, PDFs) and converted them into structured insights
- Experience with vector databases and knowledge graphs
- Understanding of the nuances of the asset management workflow
- Ability to design for scale, auditability, and fault tolerance
- Problem-solving mindset towards the 'Excel-centric' chaos of the current finance industry