Software Engineer, AI Model Enablement & Inference

Highlights

• Build efficient, production-ready implementations of frontier LLMs.
• Optimize model-specific attention and mixture-of-experts computations.
• Ship real silicon already in mass production for enterprise workloads.

Ideal candidate

A model-architecture enthusiast who loves squeezing performance from novel hardware and collaborating across compiler and engine teams to ship production AI systems.

Requirements

• Deep understanding of transformer-based LLMs including attention variants, mixture-of-experts architectures and KV-cache behavior
• Strong Python skills with hands-on experience reading, modifying and debugging model implementations in PyTorch or comparable framework
• Hands-on experience implementing, debugging and optimizing tensor operations or accelerator kernels with focus on compute, memory and numerical correctness
• Understanding of LLM inference performance including prefill/decode, batching and latency-throughput trade-offs with quantitative evaluation experience
• Ability to read and reason about Rust or C++ code when working on inference systems
• Clear technical communication and cross-team collaboration skills turning analysis into actionable engineering decisions