AI Model Optimization Architect for LLMs & Multimodal

Qualcomm; Cork; Hybrid; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Salary and equity package

Relocation support

Education Assistance

Pension scheme

Health and life insurance

Employee clubs

Job summary

QT Technologies Ireland Limited in Cork is seeking a Staff Engineer – AI Model Optimization Architect to lead end-to-end model transformation for LLMs, VLMs, diffusion, and multimodal models on Qualcomm accelerators.

You will collaborate with compiler, performance, and accuracy teams to optimize graphs, implement fusion kernels, and scale distributed inference across multi-core systems.

Qualifications

• Expert level expertise in PyTorch inference optimization.
• Hands on experience with torch.compile / TorchDynamo workflows.
• Deep understanding of transformer architectures and attention mechanisms.
• Practical experience with KVcache behavior and serving time optimizations.
• Strong foundation in computer architecture, ML accelerators and distributed systems.
• Proven ability to lead cross-functional technical efforts and influence design decisions.
• Academic background with relevant advanced degree or equivalent experience.

Responsibilities

• Architect and deliver model optimization strategies transforming PyTorch models for efficient inference on Qualcomm accelerators.
• Drive graph capture and deployment using PyTorch, ONNX, and torch.compile with model rewrites.
• Design and implement fusion kernels using DSL-based approaches (e.g., Triton) for performance critical ops.
• Co-design lowering strategies, kernel fusion, layouts, and runtime integration with teams.
• Profile and optimize LLM/VLM/diffusion inference for throughput and latency across batched inputs.
• Manage KVcache behavior and decoding strategies for long-context performance.
• Enable and optimize continuous batching and distributed inference across multi-core/multi-device systems.
• Scale model optimizations to new hardware architectures with reusable patterns and tooling.

Skills

PyTorch

Python

TorchDynamo

ONNX

Transformer architectures

KVcache

Distributed systems

C++/Python integration

Education

Bachelor's degree in Engineering, Information Systems, Computer Science

Master's degree in Engineering, Information Systems, Computer Science

PhD in Engineering, Information Systems, Computer Science

Tools

Triton

TorchDynamo tooling

Job description

QT Technologies Ireland Limited in Cork is seeking a Staff Engineer – AI Model Optimization Architect to lead end-to-end model transformation for LLMs, VLMs, diffusion, and multimodal models on Qualcomm accelerators.

You will collaborate with compiler, performance, and accuracy teams to optimize graphs, implement fusion kernels, and scale distributed inference across multi-core systems.