AI Platforms – BSc / MSc Student Position- Research Lab

Introduction

At our cutting-edge research lab, the AI Platforms Group focuses on developing innovative solutions at the intersection of AI systems and cloud infrastructure. Our work explores new horizons in AI inference, routing, KV-cache optimization, and Agentic AI middleware, tackling real scalability and cost challenges in modern AI platforms.

Your Role And Responsibilities

We are seeking highly motivated BSc and MSc students to join the AI Platforms Group, focusing on cost-efficient serving of large-scale AI inference workloads.

You will work on advanced routing strategies and KV-cache–aware optimizations in distributed inference systems, with an emphasis on improving performance, scalability, and GPU cost efficiency. You will be exposed to Kubernetes, cloud-native technologies, and modern inference frameworks, contributing to research and prototyping efforts using production-like workloads.

You’ll join llm-d, a leading open-source platform for high-performance, distributed LLM inference, led by IBM, Red Hat, Google, and NVIDIA, with broad industry collaboration.

This role requires strong technical curiosity, independence, and continuous learning, and offers a hands-on student position at IBM Research, working on real, production-grade AI inference systems.

Your Work Will Include

• Designing and evaluating routing algorithms to optimize inference latency, throughput, and cost
• Investigating KV-cache management strategies for large-scale distributed inference serving
• Prototyping, benchmarking, and analyzing inference optimization techniques
• Working with modern inference frameworks and real-world AI workloads
  
  

• Opportunities to work on high-impact research projects with a world-class team
• Exposure to state-of-the-art AI systems and cloud technologies
• A collaborative and innovative research environment bridging research and real systems
  
  

• Experience with Kubernetes (K8s) and cloud-native systems
• Familiarity with inference serving stacks, routing, scheduling, or KV-cache behavior
• Hands-on experience or knowledge of vLLM or similar inference frameworks
• Experience with benchmarking, profiling, or performance analysis
• Hands-on experience with Go, Python, or similar systems-oriented languages