AI Performance Engineer (Cloud AI Engineering), Sr | Staff | Sr. Staff - Cork, Ireland

Company: QT Technologies Ireland Limited Job Area: Engineering Group, Engineering Group > Software Engineering General Summary: AI Performance Engineer (Cloud AI Engineering)   Qualcomm is   utilizing   its traditional strengths in digital wireless technologies to play   a central role   in the evolution of Cloud AI. We are investing in several supporting technologies including Deep Learning. The Qualcomm Cloud AI team is developing hardware and software solutions for Inference Acceleration.    We are   hiring an AI   Performance Engineers at multiple levels to join our dynamic, collaborative team.   This role spans the full product lifecycle—from   cutting-edge   research and development to commercial deployment—and demands strategic thinking, strong execution, and excellent communication skills.   This role involves the following activities:   Convert,   optimize   and deploy models for efficient inference using   PyTorch , ONNX .   Work at the forefront of   GenAI   by understanding advanced algorithms ( e.g.   attention mechanisms,   MoEs ) and   numerics   to   identify   new optimization opportunities .   Performance analysis and optimization of LLM, VLM, and diffusion models for inference.  Scale performance for throughput and latency constraints.   Mapping the next generation AI workloads on top of current and future hardware designs.    Work closely with customers to drive solutions by collaborating with internal compiler,   firmware   and platform teams.   Analyze complex performance or stability issues to work towards final root cause of underlying problems .   Create engineering solutions to deliver continuous insights into performance of AI workloads guiding the improvements over time .   Design and implement high-level kernels,   e.g.   in Triton, with a focus on generating efficient, low-level code.   Candidates for this position will   demonstrate   the following:   Hands-on experience in building and   optimizing   language models, notably in   PyTorch , ONNX, preferably in production-grade environments.   Deep understanding of transformer architectures, attention   mechanisms   and performance trade-offs.   Experience in workload mapping strategies exhibiting sharding or various parallelisms .   Strong Python programming skills .   Proactive learning about the latest inference optimization techniques .   Understanding of computer architecture, ML accelerators, in-memory   processing   and   distributed   systems.   Strong communication , problem-solving   skills   and ability to learn and work effectively in a fast-paced   and   collaborative environment .   MS in Computer Science, Machine Learning, Computer Engineering or Electrical Engineering .   Bonus Skills:   Background in neural network operators and mathematical operations, including linear algebra and math libraries .   Understanding of machine learning compilers .   Experience in converging accuracy and its evaluation methods .   Knowledge of    torch.compile   or   torchDynamo .   PhD in Computer Science, Computer Engineering   or   Machine Learning     Where you will be working Cork has a proud reputation as Ireland's second largest economic engine and is now one of the Top 20 location choices in Europe with 39,000 people being employed by over 170 overseas companies. There's a growing diversity in the region with people from many nationalities relocating to Cork, relishing the opportunity to work and live in a location that offers an excellent quality of life. A gateway to Europe, Cork airport provides access to almost 50 international destinations including transatlantic air routes. Equal Opportunities We are an Equal Opportunity employer; all qualified applicants will receive consideration for employment without regard to race, colour, religion, sexual orientation, gender identity, national origin, disability, veteran status, or any protected classification.