Embedded AI Compute Engineer: NPU Modeling & Optimization

Black Sesame Technologies (Singapore) Pte Ltd; Singapore; On-site; SGD 60,000 - 100,000; Full time

Job summary

Black Sesame Technologies (Singapore) Pte Ltd seeks an Engineer, AI Computing to advance autonomous driving research. You will build high‑fidelity performance models, simulate chip behavior, and collaborate across DE/DV and compiler teams to optimize hardware and software co-design.

The role welcomes fresh graduates and offers hands‑on opportunities in CUDA‑based operator development for embedded AI platforms, with a strong emphasis on learning and cross‑disciplinary teamwork.

Qualifications

• Master’s or PhD degree in Computer Science, Electrical/Computer Engineering, or related fields.
• Fresh graduates welcome; internship, academic research, or hands‑on project experience in chip modeling or AI computing is a plus.
• Proficiency in Python, CUDA, and deep learning frameworks such as PyTorch; experience with C++ or hardware modelling tools is a plus.
• Strong problem-solving interest in system architecture and performance analysis.
• Effective communicator and team player across multidisciplinary teams.

Responsibilities

• Develop performance analysis models to identify hardware bottlenecks and propose architectural improvements.
• Build functional and execution models to simulate chip behaviours and results.
• Collaborate with design (DE) and verification (DV) teams to model modules and validate against RTL.
• Work with the compiler/model compilation team to provide optimization feedback and ensure accurate simulation results.
• Develop custom CUDA operators in PyTorch for customer-facing applications.

Skills

Python

CUDA

PyTorch

Deep Learning

Education

Master's or PhD in CS/EE or related

Tools

C++

Hardware modeling tools

Job description

Black Sesame Technologies (Singapore) Pte Ltd seeks an Engineer, AI Computing to advance autonomous driving research. You will build high‑fidelity performance models, simulate chip behavior, and collaborate across DE/DV and compiler teams to optimize hardware and software co-design.

The role welcomes fresh graduates and offers hands‑on opportunities in CUDA‑based operator development for embedded AI platforms, with a strong emphasis on learning and cross‑disciplinary teamwork.