EngineerJobs.io
← Back to all jobs

Job Description

Work on the intelligence layer of Link’s Analytics Engine and help make real estate data reliably queryable by LLMs. This hybrid role in New York, NY combines ML, backend engineering, and data systems to deliver insights to investment teams in real time. You will design graph-based structures, retrieval pipelines, and production services with a strong focus on trust, provenance, and low-latency reliability.

What you’ll deliver

  • Graph-based data structures that encode relationships across markets, assets, tenants, and transactions.
  • Retrieval pipelines that support RAG, hybrid search, and structured queries so LLMs get accurate, context-rich grounding.
  • Rule-based and agentic LLM workflows that automate investment analytical tasks.
  • Production-ready prompt engineering, eval frameworks, and reliability ownership for LLM workflows.

Data pipelines and trustworthy outputs

  • ETL/ELT workflows to ingest, normalize, and enrich large-scale internal and third-party datasets including property records, leasing data, macro signals, and alt data.
  • Clear data ownership, update cadence, and quality SLAs for every dataset.
  • Trust-by-design systems: lineage tracking from source to insight, confidence scoring for derived outputs, and attribution so analysts can see where a number came from and how fresh it is.
  • Operational rigor: treat bad compensation inputs or stale signals as production incidents.

APIs, latency, and collaboration

  • APIs and services that expose ML outputs and structured data to front-end applications.
  • A focus on low-latency, reliability, and clean contracts with the application team.
  • Work directly with investment and asset management teams to understand analytical needs and iterate quickly.
  • Treat analyst trust as a first-class product requirement.

What you bring

  • 4+ years in ML engineering, backend engineering, or a role spanning both.
  • Hands-on experience shipping LLM-powered applications in production, including RAG pipelines, prompt engineering, and eval frameworks.
  • Strong Python skills, with comfort owning backend services and APIs end-to-end.
  • Experience with knowledge graphs or graph databases (for example, Neo4j).
  • Proficiency building data pipelines at scale (such as Spark and Databricks).
  • Deep sensitivity to data provenance, including a track record of building systems that create analyst trust.

Technologies: Python, Neo4j, Spark, Databricks, RAG, hybrid search.

Compensation and benefits

Salary range: USD 165,000 - 185,000 per year (anticipated base compensation range).

  • Health insurance coverage
  • Retirement savings plan
  • Paid holidays
  • Paid time off

Similar Jobs