Elevate AI workloads with Baseten as an Inference Performance Engineer. Focus on optimizing cutting-edge inference techniques while working in a energetic, fast-paced environment. At Baseten, we're seeking an Inference Performance Engineer committed to improving AI model performance.

This role requires expertise in runtime internals and includes skills such as quantization, decoder specs, and KV-cache management. You’ll be directly impacting how our customers’ models run and how efficiently we serve them. Key Responsibilities:

- Implement advanced inference techniques for runtime optimization
- Optimize end-to-end performance, identifying bottlenecks
- Provide clear latency/throughput/cost tradeoffs to stakeholders
- Bring up new model architectures on release day
- Develop benchmarking frameworks for performance measurement Requirements:
- Degree in Computer Science, Engineering, or related field
- Proficient in Python, C++, or similar languages
- Familiarity with LLM optimization techniques
- Strong experience with ML libraries like PyTorch
- Deep understanding of GPU architecture Make a significant impact on AI performance with your expertise in inference techniques at Baseten.

📌 Inference Performance Engineer at Baseten (Montreal)
🏢 Baseten
📍 Montreal