Backend Engineer - Recommendation (all genders)

Develop the recommendation engine powering ABOUT YOU's homepage, product, and outfit pages in Node.js/TypeScript
Serve offline-trained ML models (matrix factorization, brand similarity, image embeddings) at Black-Friday scale from Valkey, DynamoDB, and OpenSearch
Design personalization logic: feed assembly, fallback chains, deduplication, diversity, and A/B experimentation
Build GenAI product features like our streaming Gemini fashion advisor, focusing on low latency, session state, and token cost control
Own reverse-ETL pipelines that move BigQuery model outputs into high-performance hot stores
Instrument recommendation coverage, track business metrics via SQS/BI systems, and shape architecture alongside our Tech Lead
You take end-to-end responsibility for our recommendation engine and love seeing your changes directly impact customer engagement
3+ years of experience building high-throughput backend services (Node.js/TypeScript preferred, or fast-converting from Java, Go, or Kotlin)
Real depth in Redis/Valkey data modeling, caching hierarchies (multi-tier, TTLs/invalidation), and binary payloads (Protobuf/Avro)
High-throughput mindset: comfortable operating APIs that scale to 10k+ rps under strict latency SLOs
You're excited to bridge backend engineering and ML by serving model scores, embeddings, or LLM features in live systems
Clear communication skills in English and a data-driven, experiment-friendly mindset
Nice to Have
RecSys fundamentals (collaborative filtering, matrix factorization, cold-start handling, diversity algorithms)
Streaming GenAI / LLM product experience (chat UX, prompt caching, guardrails)
Experience with AWS serverless (DynamoDB modeling, SQS/SNS) and OpenSearch k-NN indices
Performance profiling (clinic.js, flamegraphs) and load testing (k6)

Employment type
Full-time

Work arrangement
Hybrid