AI Platform & Inference Suite Engineer – Staff/Senior Staff

About the role

Qualcomm is looking for a senior‑level AI Platform & Inference Suite Engineer to enable rack‑scale deep‑learning workloads on its AI inference accelerators. The role is customer‑facing and highly technical, focusing on porting, optimizing, and validating AI models for data‑center deployments using popular frameworks.

Key responsibilities

• Port, convert, and quantize deep‑learning models (INT8 / mixed precision) for accelerator‑based platforms.
• Evaluate model throughput, latency, and accuracy; profile and optimize performance.
• Integrate models from PyTorch, TensorFlow, and ONNX into Qualcomm Cloud AI stack.
• Build, test, and deploy scalable inference pipelines using serving frameworks.
• Collaborate with customers to size hardware, guide deployment decisions, and ensure production readiness.
• Document processes, create training material, and deliver technical demonstrations.

Required profile

• Strong expertise in AI model development, quantization, and performance optimization.
• Experience with deep‑learning workloads across hardware platforms.
• Solid programming background and ability to work with cross‑functional teams.
• Proficiency in Linux environments and container orchestration tools.
• Ability to translate customer requirements into hardware‑compatible solutions.

Required skills

• PyTorch
• TensorFlow
• ONNX
• Linux
• Container orchestration (e.g., Kubernetes)
• AI model quantization (INT8, mixed precision)
• Performance profiling and optimization
• Deep‑learning model development