Staff AI Model Optimization Architect — Scalable Inference

Qualcomm; Cork; On-site; EUR 150,000 - 190,000; Full time

Benefits offered by this job

Salary and stock bonus

Relocation assistance

Education assistance

Pension matching

Insurance (life/medical)

Well-being subsidies

Employee stock purchase

Job summary

QT Technologies Ireland Limited is seeking a Staff Engineer to lead end-to-end model transformation and optimization for LLMs, VLMs, diffusion, and multimodal models on Qualcomm accelerators.

You will collaborate with compiler, performance, and accuracy teams to transform models into accelerator-efficient execution, balancing throughput, latency, and memory while ensuring production readiness across Day0 to deployment.

Qualifications

• Expert level expertise in PyTorch and inference-focused model optimization.

Responsibilities

• Architect and deliver model optimization strategies for PyTorch models on Qualcomm accelerators.
• Drive graph capture and deployment with PyTorch, ONNX, torch.compile.
• Design and implement fused kernels using DSL approaches (e.g., Triton).
• Partner with compiler, performance, and accuracy teams on lowering strategies and runtime integration.
• Profile and optimize LLM/VLM/diffusion inference for throughput and latency across configurations.
• Own transformer optimizations including KVcache management and long context performance.
• Enable continuous batching and scheduling to optimize memory and tail latency.
• Architect and scale distributed inference strategies across multi-core/multi-device systems.
• Establish reusable patterns and tooling for scaling model optimizations to new hardware.
• Debug complex performance or stability issues to production-ready solutions.

Skills

PyTorch

Python

TorchDynamo

Graph compilation

Transformer optimization

KVcache

Distributed systems

C++/Java

CPU/GPU architectures

Education

Bachelor's degree in Engineering/CS/EE

Master's degree in Engineering/CS/EE

PhD in Engineering/CS/EE

Tools

PyTorch

ONNX

Triton

TorchDynamo

Job description

QT Technologies Ireland Limited is seeking a Staff Engineer to lead end-to-end model transformation and optimization for LLMs, VLMs, diffusion, and multimodal models on Qualcomm accelerators.

You will collaborate with compiler, performance, and accuracy teams to transform models into accelerator-efficient execution, balancing throughput, latency, and memory while ensuring production readiness across Day0 to deployment.