Senior Search Applications Performance Engineer
Core
Optimize and scale search applications and infrastructure to ensure fast, reliable, and intelligent search experiences for AI-powered systems.
Role type
Senior Search Applications Performance Engineer
Builds
Compass search services, integration with North, and tool surfaces for agentic users
Domain
AI/LLM infrastructure, search technology, performance engineering
Deliverable
production ML models | infrastructure
Required skills
Python, backend search technologies (OpenSearch, ElasticSearch, Weaviate, FastAPI), data/evaluation pipelines, performance benchmarking, application profiling (CPU/GPU/autoscaled nodes)
Preferred skills
Kubernetes, Helm, infrastructure deployment, GPU-based model inference optimization (ONNX, Triton, vLLM), search and discovery domain experience
Technologies
OpenSearch, ElasticSearch, Weaviate, FastAPI, Kubernetes, Helm, ONNX, Triton, vLLM
Responsibilities
Implement performance monitoring and optimization strategies for search services, develop and maintain benchmarking frameworks, collaborate with modeling teams to optimize search models, scale search services while maintaining high availability and low latency, partner with product teams to translate performance requirements into technical implementations, develop and optimize new tool surfaces for agentic search experiences
Seniority
Senior, hands-on IC