Empower cutting-edge AI solutions at Baseten as an AI Model Engineer. Focus on the development and optimization of APIs essential for high-performance model inference.

Join Baseten’s Model Performance team, where your work will ensure fast, reliable, and cost-productive deployment of AI models. Ideal for candidates skilled in distributed systems and backend infrastructure, this role is pivotal in shaping how developers interact with AI technologies.

Key Responsibilities

- Architect and manage Model APIs with advanced inference features
- Optimize performance of TensorRT-LLM and CUDA kernels
- Drive production-level performance enhancement initiatives
- Develop comprehensive benchmarking frameworks for AI models
- Foster collaboration to deliver robust model serving solutions

Requirements

- 3+ years in managing distributed systems or APIs
- Track record of low-latency backend service development
- Profound knowledge of profiling, tracing, and SLO management
- Expertise in troubleshooting complex system interactions
- Strong writing skills for effective design documentation

Become a key player in advancing AI model performance at Baseten.

📌 AI Model Engineer at Baseten (Montreal)
🏢 Baseten
📍 Montreal