AI Model Optimization Architect

Staff AI Engineer | Hybrid | $158,400.00 - $237,600.00 We're hiring on behalf of a Haystack partner! The Role • Lead end-to-end model transformation and optimization for large AI models on inference accelerators. • Architect and deliver PyTorch model optimization strategies for efficient inference. • Drive graph capture and deployment using PyTorch, ONNX, and torch.compile. • Design and implement fusion kernels using DSL-based approaches (e.g., Triton). • Profile and optimize LLM/VLM/diffusion inference for throughput and latency. • Establish reusable approaches to scale model optimizations to new hardware architectures. What You'll Need • Expert-level expertise in PyTorch and inference-focused model optimization. • Hands-on experience with torch.compile / TorchDynamo or related graph compilation workflows. • Deep understanding of transformer architectures and performance trade-offs. • Practical experience with KVcache behavior and serving time optimizations. • Strong foundation in computer architecture, ML accelerators, and distributed systems. • MS in Computer Science, Machine Learning, or a related engineering field, or equivalent experience. What's On Offer • Competitive annual discretionary bonus program. • Opportunity for annual RSU grants. • Highly competitive benefits package designed to support well-being. Apply via Haystack today!