Staff AI Systems Engineer

About the role

Reporting directly to the AI Architect, the Staff AI Systems Engineer will serve as a key technical partner in translating AI product requirements and architectural vision into deployable AI solutions.

Key responsibilities

• Drive hardware/software co‑design across machine‑learning algorithms, software frameworks, compiler support, system architecture, and silicon capabilities.
• Evaluate emerging AI workloads, perform roofline and performance‑bottleneck analysis, and study model‑optimization techniques such as quantization, sparsity, pruning, and compression.
• Collaborate with IC Design, Software Engineering, and System Engineering teams to assess architectural trade‑offs, influence future hardware capabilities, develop performance models and benchmarks, and validate concepts through simulation and FPGA‑based prototyping.

Required profile

• Master's or PhD in Computer Engineering, Electrical Engineering, Computer Science, Machine Learning or related discipline.
• 8+ years of experience in AI systems, computer architecture, machine‑learning deployment, or semiconductor development.
• Experience developing or evaluating NPU architectures and familiarity with Verilog, SystemVerilog, architecture simulation, performance modeling, and design‑space exploration.
• Hands‑on experience with MLIR, TVM, ONNX Runtime, TensorRT, OpenVINO or similar deployment frameworks.
• Background in computer‑vision, imaging pipelines, AI‑enabled sensor systems, and knowledge of RISC‑V Vector or SIMD architectures.
• Publications, patents or open‑source contributions in AI systems or computer architecture; proven ability to lead cross‑functional technical initiatives.

Required skills

• Python
• C/C++
• Verilog & SystemVerilog
• MLIR, TVM, ONNX Runtime, TensorRT, OpenVINO
• FPGA prototyping and performance analysis
• Model compression techniques (quantization, sparsity, pruning, compression)
• Compiler‑aware optimization
• RISC‑V Vector and SIMD architectures