Staff Applied AI Engineer
Software Engineering, Data Science · Full-time
San Jose, CA, USA
USD 230k-270k / year + Equity
As a Staff Applied AI Engineer on FloQast's Data Platform team, you'll be a key technical leader setting the direction for how documents become connected, queryable data across our products. In this role you'll focus on AI products and data intelligence, applying modern AI and machine learning to the financial data and documents our customers work with every day. You will define the standards and patterns for document processing, retrieval, and context engineering that our AI agents and products rely on.
You've spent years shipping document AI and retrieval systems from prototype to production. You've built pipelines that parse, chunk, and embed unstructured documents, designed retrieval and reranking that hold up on real workloads, and built evaluation frameworks that tell you whether a change actually made the system better. You make clear build-versus-buy calls on AI components and own the result in production. At this level, you don't just build systems. You set the quality bar and the architecture others build on.
At FloQast, you'll apply that depth on top of our lakehouse and AI stack. Our data lives in Iceberg on S3, orchestrated through Airflow on MWAA and queried via Trino and Athena, and the systems you design will serve products used by 3,000+ tenants. You'll work with data platform and product leaders, mentor engineers, and help connect documents, knowledge graphs, and structured data into context our AI can trust.
FloQast is headquartered in Los Angeles & San Jose, CA and we are seeking US-based Hybrid Engineers.
What You'll Do
• Design and build document processing, retrieval and context engineering systems end to end
• Define how we measure extraction and retrieval quality, and build the eval framework
• Own production serving for these systems, including latency, cost and reliability
• Mentor engineers, review designs, and work with product and data platform leaders
• Choose build-versus-buy for AI components and document the decisions
What You'll Bring
• Shipped document AI or RAG systems at scale (parsing, chunking, embeddings, retrieval, reranking)
• Experience with unstructured data and context engineering for LLM applications
• Experience with modern agentic frameworks
• General knowledge of knowledge graphs
• Experience designing evals for LLM systems
• Strong Python and production AWS experience
• Experience with data pipelines (Spark, Airflow) and backend services
• Technical leadership across teams and time zones, with a strong sense of ownership from idea to production
Here’s Why You Should Apply
- What is engineering working on? Our FQ Engineering Blog showcases a number of our recent efforts straight from the engineers working on them. Check it out!