Senior Researcher: AI Computing Systems

Darum lohnt es sich

From its research hubs in Zurich and Lausanne, pioneering teams push the boundaries of High-Performance Computing, Computer Architecture, Computer Vision, Robotics, Artificial Intelligence, Neuromorphic Computing, Wireless Technologies, and Networking - architecting the intelligent systems that will define tomorrow’s digital era. /p pWe are looking for a strong researcher with hands‑on LLM + RAG experience who can help build and optimize techniques such as KV‑cache precomputation, KV reuse/blending (e.g., CacheBlend‑style), and sparse attention / selective recompute.

You will work close to the metal (attention kernels + profiling) and at the system level (vLLM/LMCache‑style stacks), turning research ideas into robust, high‑performance code. /p h3Responsibilities: /h3 ul lipDesign and implement RAG acceleration techniques that reduce TTFT and improve throughput (e.g., document KV precomputation, reuse, caching policies). /p /li lipDevelop KV‑cache reuse / blending pipelines and integrate them into inference stacks (batching, paging, eviction, correctness/quality trade‑offs). /p /li lipImplement and optimize sparse attention / selective attention paths, including mask construction and block‑granularity strategies. /p /li lipWork with PyTorch and modern attention backends/kernels (e.g., FlashAttention / FlashInfer‑like kernels), profiling and optimizing performance. /p /li lipStay up to date with the latest research and open‑source progress in LLM inference, KV caching, and RAG systems, and translate it into practical improvements. /p /li /ul h3Qualifications: /h3 ul lipPhD in Computer Science, Electrical Engineering, or a related field. /p /li lipStrong software engineering skills in Python, with substantial PyTorch experience (model internals, attention/KV cache concepts, performance‑aware coding). /p /li lipSolid understanding of transformer inference fundamentals: prefill vs decode, KV cache layout, masking, batching, latency/throughput trade‑offs. /p /li lipExperience benchmarking and profiling AI LLM workloads, and diagnosing performance bottlenecks. /p /li lipbStrong communication skills and comfort collaborating across research + engineering.br/ /b /p /li /ul h3Preferred Qualifications (Nice to Have): /h3 ul lipExperience with vLLM and/or LMCache (integration, debugging, extending attention/KV‑cache logic). /p /li lipFamiliarity with attention kernel stacks and customization (FlashAttention/FlashInfer, Triton, CUDA extensions, custom ops). /p /li lipPractical experience building RAG pipelines (retrieval, chunking, indexing, reranking) and understanding how retrieval interacts with inference latency. /p /li lipContributions to open‑source projects or publications/technical reports in AI systems, LLM inference, caching, or storage‑aware ML systems. /p /li lipSystems background (Linux, performance engineering, storage/IO, memory hierarchy) and comfort working close to hardware. /p /li /ul h3Why join us: /h3 ul lipCollaborate with world‑class scientists and engineers in an open, curiosity‑driven environment. /p /li lipAccess to state‑of‑the‑art technology and tools. /p /li lipOpportunities for professional growth and development. /p /li lipCompetitive salary, and a high quality of life in Zurich, at the center of Europe. /p /li lipLast but certainly not least: be part of innovative projects that make a difference. /p /li /ul /p #J-18808-Ljbffr ppbHuawei envisions a world where technology connects people, empowers industries, and unlocks human potential. /bGuided by its mission to enrich lives through communication and intelligent innovation, Huawei stands at the forefront of global digital transformation.

As a leader in Information and Communications Technology (ICT), the company pioneers breakthroughs in artificial intelligence, cloud computing, and smart devices - building the intelligent foundation of a fully connected world. /p pThrough its Carrier, Enterprise, and Consumer business groups, Huawei delivers resilient digital infrastructure, advanced cloud and AI platforms, and transformative devices that enable progress at every level.

Supporting 45 of the world’s top 50 telecom operators and serving one-third of the global population across more than 170 countries, Huawei is shaping a future where connectivity becomes a powerful catalyst for opportunity and sustainable growth. /p pThis spirit of bold innovation is embodied by Huawei Technologies Switzerland AG.