Senior Search Applications Performance Engineer

Stack

Responsibilities

• ▹Implement performance monitoring and optimization strategies for Compass search services and the integration with North
• ▹Develop and maintain benchmarking frameworks to evaluate search model performance and infrastructure efficiency
• ▹Collaborate with modeling teams to optimize search models for faster response times and reduced resource consumption
• ▹Work on scaling the 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

Requirements

• ▹Proficiency in Python and backend search technologies (OpenSearch, ElasticSearch, Weaviate, FastAPI)
• ▹Experience with data or evaluation pipelines and performance benchmarking
• ▹Experience profiling applications hosted on a mix of CPU, GPU, and autoscaled compute nodes
• ▹Ability to communicate technical performance metrics effectively to cross-functional teams
• ▹4+ years of experience contributing to production environments

Nice to have

• ▹Experience with Kubernetes, Helm, and infrastructure deployment
• ▹Familiarity with GPU-based model inference optimization (ONNX, Triton, vLLM)
• ▹History working in the search and discovery domain

Soft skills

What we offer

• ▹Weekly lunch stipend ($75/£75 or local currency equivalent)
• ▹Full health and dental benefits, including a separate mental health budget
• ▹RRSP matching, 401K, Pension Scheme
• ▹100% Parental Leave top-up for up to 6 months
• ▹Annual enrichment benefits, education & learning stipend
• ▹6 weeks of paid vacation (30 working days)
• ▹$500 home office stipend, co-working benefit for those not near an office

About the company

Cohere is the leading security-first enterprise AI company, building cutting-edge foundation AI models and end-to-end products that solve real-world business problems. A global technology company co-headquartered in Toronto and San Francisco, with offices in London, New York City, Montreal, Seoul, Germany, and Paris.