SDE II - ML
Core
Build core systems for Glance's AI shopping agent, focusing on low-latency ML inference, automated evaluation, and rapid prototyping.
Role type
Senior IC machine learning engineer (ML infrastructure & serving)
Builds
Low-latency ML inference platforms, automated evaluation harnesses, and scalable platform components for AI shopping features.
Domain
E-commerce, AI/ML, Recommendation Systems
Deliverable
production ML models
Required skills
Python, distributed systems, model serving (Triton, vLLM, TorchServe), vector databases (Qdrant, Faiss), feature stores, system profiling, query performance tuning, ML monitoring
Preferred skills
Experience with recommendation pipelines, shadow deployment setups, high-throughput production ML systems, 0→1 prototyping
Technologies
Vertex AI, Gemini, Imagen, InMobi
Responsibilities
Build and scale systems for recommendation inference, vector search, and real-time data updates; Develop automated offline/online evaluation frameworks and regression tests; Optimize throughput and reduce serving latency across CPU/GPU clusters; Partner with applied scientists to deploy experimental models to production.
Seniority
Mid-level IC (3+ years SE, 2+ years ML infra)
