1 day ago
Hanoi, Vietnam or Ho Chi Minh City, VietnamMid Level / Senior
Responsibilities
- Evaluate LLMs, VLMs, diffusion models, and multimodal models and onboard them to Qualcomm AI software stacks and target platforms.
- Enable quantization, model adaptation, graph conversion, profiling, memory analysis, and runtime performance optimization.
- Perform on-device validation, downstream benchmarking, and performance analysis against latency, memory, power, and accuracy requirements.
- Debug issues across model, quantization, runtime, backend, compiler, platform, and system layers with partner engineering teams.
- Support rapid inference prototyping for new model architectures and deliver production-ready on-device AI experiences.
- Create technical documentation, benchmark reports, debugging notes, and onboarding guides.
Requirements
- Bachelor’s or master’s degree in Computer Science, Electrical Engineering, Artificial Intelligence, Machine Learning, or a related technical field, or a PhD in a related field.
- At least 4 years of related Hardware Engineering, Software Engineering, Systems Engineering, or equivalent work experience with a bachelor’s degree; 3+ years with a master’s degree; or 2+ years with a PhD.
- Hands-on experience with AI/ML model deployment, optimization, benchmarking, or software development for edge, mobile, compute, or embedded platforms.
- Strong understanding of LLM, vision-language, diffusion, or multimodal model architectures.
- Experience with quantization, graph conversion, profiling, memory analysis, runtime tuning, benchmark analysis, and performance trade-off evaluation.
- Familiarity with AI software stacks, inference runtimes, hardware accelerators, and cross-stack debugging workflows.
- Preferred experience with Qualcomm AI software stacks, QNN, NPU acceleration, edge AI deployment toolchains, and onboarding or benchmarking modern GenAI architectures.
- Strong ownership, problem-solving, debugging, communication, and cross-functional execution skills.
Categories
About Qualcomm
Qualcomm is a public semiconductor company headquartered in San Diego, founded in 1985, that designs and sells wireless chipsets and platforms for mobile devices, automotive, IoT, and networking, notably the Snapdragon application processors and 5G modems. It also licenses a large portfolio of cellular patents to device makers, generating revenue alongside chip sales; its technology underpins many Android smartphones and emerging automotive and edge-compute systems, and it trades on NASDAQ as QCOM.