Design the retrieval and ranking systems that power product discovery for millions of users, balancing cutting-edge ML with real-time performance constraints
Job Summary
Design the retrieval and ranking systems that power product discovery for millions of users, balancing cutting-edge ML with real-time performance constraints.
Architect multi-model inference pipelines optimized for latency-sensitive workloads and define relevance metrics, run A/B experiments, and drive measurable business outcomes.
Support the driving MLOps standards for model deployment, monitoring, and continuous improvement, and partner with Product, Merchandising, and Engineering to translate business requirements into ML solutions.
Matching Summary
Design the retrieval and ranking systems that power product discovery for millions of users, balancing cutting-edge ML with real-time performance constraints.
Skills & Requirements
Must-have
ML-first search architecture
embedding models
vector similarity
cross-encoder reranking
MLOps standards
transformer-based models
Nice-to-have
enterprise search platforms
Learning-to-Rank
multi-stage retrieval architectures
Cloud ML platform experience
Key Requirements
7+ years in software, data, or ML engineering
3+ years building production search systems
Experience with e-commerce search patterns
Hands-on experience with vector databases
MLOps expertise
Production experience with transformer-based models
Track record balancing latency, cost, and relevance tradeoffs