Senior Applied Data Scientist (Retrieval and Semantic Systems)
InstructureJob Description
📋 Description Design, build, and ship production retrieval systems. Own vector store selection and operation (scalability, latency, multi-tenant). Build and operate indexing/refresh pipelines: chunking, embeddings, backfills. Implement semantic and hybrid retrieval: embeddings, similarity search, filtering, reranking. Own retrieval evaluation as a first-class system: gold sets, drift detection. Balance relevance, latency, cost, and operational complexity. 🎯 Requirements 6+ years of experience building and shipping production ML or applied AI systems. Proven ownership of a retrieval system in production, incl. vector store selection and operation. Strong Python skills and API development (e.g., FastAPI). Solid grounding in embeddings, ANN search, and retrieval/ranking systems. Experience designing indexing and refresh strategies with data quality controls and safe backfills. Demonstrated ability to define and run retrieval evaluation and prevent regressions. 🎁 Benefits Competitive compensation plus ownership program. Flexible remote, hybrid, and in-office work culture. Generous time off and holidays. Wellness programs and mental health support. Learning and development tools with tuition reimbursement. Tools to do your best work and recognition program.