H

Research Scientist – AI Performance Optimization and Systems

Huawei·Zürich·13.11.2026

 careers.huaweirc.ch

 
 
full_time80–100%
Job written in
English
Location
Zürich
Work type
On-site
Type
Full-time

 

Huawei's European Research Institute (ERI) is a global ICT leader with more than 1,500 researchers across Europe. The Swiss laboratory focuses on next‑generation computing architectures, hardware, software and algorithms for the AI era, partnering with universities and industry to drive fundamental breakthroughs. The team works at the crossroads of efficient AI, generative models and distributed systems, aiming to make large multimodal and video‑generation workloads practical on modern platforms. The role is a hands‑on Research Scientist dedicated to AI performance optimisation. You will investigate and improve the execution of large AI models, from low‑level kernels and frameworks to full end‑to‑end systems. Key activities include formulating research problems, building prototypes, running large‑scale experiments, measuring latency, throughput, memory use and hardware utilisation, and publishing results. Experienced hires may also co‑supervise interns and assist with recruitment. Day‑to‑day work involves developing techniques that boost latency, throughput, memory efficiency and hardware utilisation across AI workloads. Typical tasks are end‑to‑end optimisation of large‑model inference, AI‑agent‑driven profiling and benchmarking, compiler and operator optimisation (e.g., kernel fusion, low‑precision execution), distributed inference with communication‑compute overlap, and hardware‑software co‑design for emerging accelerators. You will implement and optimise model execution on large NPU/GPU clusters, define representative benchmarks, turn research outcomes into real‑time demos and deployable systems, publish at top conferences and contribute to open‑source projects. The must‑have qualifications are a PhD (or equivalent industry research experience) in Computer Science, Electrical Engineering, AI, Machine Learning or a related discipline, plus a record of research publications or demonstrable industry impact in AI systems, efficient ML or compilers. You must have proven hands‑on experience delivering measurable improvements in latency, throughput, memory consumption or hardware utilisation, strong Python programming skills and familiarity with at least one ML, compiler or systems stack. Experience profiling, benchmarking and diagnosing performance bottlenecks in ML workloads, the ability to conduct independent research from idea to implementation, and clear written and oral communication are also required. Nice‑to‑have expertise includes AI‑agent‑driven optimisation (automated profiling, scheduling, caching), work on distributed inference and GPU/NPU memory optimisation, compiler techniques such as kernel fusion and low‑precision inference (FP8/FP4), long‑context inference, sparse attention or MoE acceleration, optimisation of generative models, multimodal streaming video systems, and contributions to open‑source AI frameworks or compilers. The position offers close collaboration with leading academic and industry researchers, access to large‑scale AI models and cutting‑edge computing resources, and the chance to influence the team's research direction. What the role asks for: - PhD in CS, EE, AI, ML or related field - Research publications or proven industry impact in AI systems - Hands‑on experience improving AI model latency, throughput or memory - Strong Python programming skills - Experience with at least one ML, compiler or systems stack - Proven profiling and benchmarking of ML workloads - Ability to conduct independent end‑to‑end research - Clear written and oral communication - Nice‑to‑have: AI‑agent‑driven optimisation experience - Nice‑to‑have: Distributed inference and GPU/NPU memory optimisation - Nice‑to‑have: Compiler optimisation such as kernel fusion or low‑precision inference - Nice‑to‑have: Contributions to open‑source AI frameworks or compilers

 

 

 

 

 

Kostenlos

Scientist: Lebenslauf-Vorlage

Bewirb dich mit einem Lebenslauf im Schweizer Aufbau — mit Beispieltext und den Anforderungen, die Scientist-Inserate am häufigsten nennen.

Lebenslauf-Vorlage Schweiz ansehen

Scientist: was der Markt gerade verlangt

Scientist-Stellen gehören zu den regelmässig ausgeschriebenen Berufen auf SwissJobs.app.

Weitersuchen

Ähnliche Jobs per E-Mail erhalten