Orderfox is hiring a Lead Data Architect to architect the data platform behind our AI-powered market intelligence agent. You will drive the vision, ship early iterations, boost performance, and help define innovation, not just support it.

What You'll Do

Re-architect the web-to-profile pipeline, designing distributed crawling systems with polite scheduling and deduplication.
Co-design and evolve a multimodal knowledge base combining Postgres, pgvector, Cosmos DB Graph, DuckDB, and others to serve SQL, graph, and semantic queries with sub-second latency.
Build LLM-powered enrichment chains, developing RAG and tool-calling pipelines that convert raw documents into structured profiles and guide prompt and chain versioning.
Integrate and steward diverse data sources (finance, trade, product catalogues), negotiate contracts, resolve entities, and define refresh cadence.
Implement data operations and observability: CI/CD for data (GitHub Actions + dbt/Airflow), lineage (OpenLineage), and cost and quality dashboards.
Mentor and collaborate cross-functionally, translating product questions into schemas, shaping the roadmap, and supporting peer growth.
Lead technically while staying hands-on, working closely with the CTO and growing into a player-coach leadership role as the team scales.

What We're Looking For

Extensive experience designing end-to-end data architectures at web scale – from raw HTML through SQL, graph, or vector databases to production-grade APIs.
Proficient in modern, high-performance Python (async, typed), and comfortable with Spark / Dask for large transforms.
Solid track record developing distributed web crawlers and anti-bot strategies using Firecrawl, Playwright or Crawlee.
Deep understanding of LLM / RAG engineering with Semantic kernel / LangChain / LlamaIndex, prompt and chain versioning.
Working knowledge of Azure lakehouse stack (Blob, Data Lake, Fabric) or similar cloud platform and open table formats (Delta/Iceberg).
Strong communicator with the ability to clearly explain complex data topics to both executives and colleagues.

Technical Stack

Languages & Frameworks: Python, Spark, Dask
Databases: Postgres, pgvector, Cosmos DB Graph, DuckDB
Crawling: Firecrawl, Playwright, Crawlee
LLM Tooling: Semantic Kernel, LangChain, LlamaIndex
Cloud & Data Platforms: Azure Blob, Azure Data Lake, Microsoft Fabric, Delta, Iceberg
Data Ops: GitHub Actions, dbt, Airflow, OpenLineage

Team & Environment

You will join a ~30-person team with a flat hierarchy where initiative beats bureaucracy. You will work closely with and report directly to the CTO.

Benefits & Compensation

Real-world impact in industrial AI, contributing to Gieni AI’s multi-agent infrastructure and Microsoft Copilot integration.
Modern tech stack with autonomy to co-own a greenfield stack and choose the right tool for the job.
Flat hierarchy in a ~30-person team.
Gorgeous Zurich HQ and flexibility with lakeside office and hybrid/abroad work options.
Personal growth with structured onboarding and clear paths to player-coach or other leadership tracks.