Senior/Staff AI Model Optimization Architect (Hsinchu/Taipei)

Technology, Data & Digital · Data, AI & Analytics · Machine Learning · Data Engineering · Software Engineering

In short

Qualcomm is seeking a Senior/Staff AI Model Optimization Architect to lead model transformation and optimization for large-scale AI models on their inference accelerators. This role involves deep collaboration with compiler and performance teams to ensure efficient execution, balancing throughput, latency, memory, and quality across the model lifecycle and future architectures.

Responsibilities

Architect and deliver model optimization strategies to transform PyTorch models for efficient inference on Qualcomm accelerators.
Drive graph capture and deployment using PyTorch, ONNX, and torch.compile, including model rewrites and graph-level transformations.
Design and implement fusion kernels using DSL-based approaches (e.g., Triton) for fused operations and performance-critical algorithmic rewrites.
Partner deeply with compiler, performance, and accuracy teams to co-design lowering strategies, kernel fusion, layout decisions, and runtime integration.
Profile and optimize LLM/VLM/diffusion inference for throughput and latency across various batch sizes, sequence lengths, and serving modes.
Own transformer-specific optimizations including KVcache management, decoding behavior, and long context performance.
Enable and optimize continuous batching, understanding its impact on memory, scheduling, and tail latency.
Architect and scale distributed inference strategies (e.g., sharding and parallelism) across multi-core and multi-device systems.
Establish reusable approaches to scale model optimizations to new hardware architectures, creating robust patterns and tooling.
Debug complex performance or stability issues to root cause and drive production-ready solutions.

Requirements

Expert level expertise in PyTorch and inference-focused model optimization; strong Python engineering skills.
Hands-on experience with torch.compile / TorchDynamo or related graph capture and compilation workflows.
Deep understanding of transformer architectures, attention mechanisms, MoEs, and performance trade-offs.
Practical experience with KVcache behavior, serving time optimizations, and memory/performance tradeoffs.
Strong foundation in computer architecture, ML accelerators, and distributed systems.
Proven ability to lead cross-functional technical efforts and influence design decisions.
MS in Computer Science, Machine Learning, Computer Engineering, or Electrical Engineering, or equivalent experience.
Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 4+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.
OR Master's degree in Computer Science, Engineering, Information Systems, or related field and 3+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.
OR PhD in Computer Science, Engineering, Information Systems, or related field and 2+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.

Desired Qualifications

Experience developing fusion kernels using Triton or similar DSLs, and collaborating with ML compiler teams.
Familiarity with LLM serving stacks and continuous batching systems.
Background in numerical methods, performance/accuracy trade-off analysis, or evaluation frameworks.
PhD in a relevant field.

Benefits

Qualcomm is an equal opportunity employer.
Commitment to providing an accessible process for individuals with disabilities.
Reasonable accommodations to support individuals with disabilities to participate in the hiring process.

Skills

PythonPyTorchONNXTriton

#AI#Model Optimization#Architecture#Machine Learning#Inference#LLM#VLM#Diffusion Models#Multimodal Models#PyTorch#ONNX#Triton#Kernel Fusion#Compiler#Performance#Latency#Memory#Quality#Transformer#KV Cache#Continuous Batching#Distributed Inference#Hardware#Software