Open position
Infrastructure

(Senior) Distributed Systems Engineer (AI)

Own the architecture of our AI inference and distributed execution infrastructure, running LLM inference efficiently and at scale in customer environments.

HybridFull-time

Daisytuner is building the software layer for the next generation of computing. We make complex software run efficiently on any processor, from CPUs and GPUs to novel accelerators, using a self-learning compiler and cloud-scale optimization infrastructure.

Our team brings together researchers and engineers from RWTH Aachen, TU Munich, TU Darmstadt, and ETH Zurich to tackle some of the hardest problems in systems and infrastructure software. If you want to work on deeply technical challenges with real-world impact, join us and help shape the future of compute.

The Role

As (Senior) Distributed Systems Engineer (AI), you own the architecture and development of Daisytuner's AI inference and distributed execution infrastructure. You define how inference engines, model serving systems and distributed compute resources work together to run LLM inference efficiently and at scale in customer environments.

You work at the intersection of AI infrastructure, distributed systems and backend engineering. You take technical ownership of the inference and execution architecture, from selecting and integrating inference frameworks to workload scheduling, resource management and failure handling. You also define how it all connects to Daisytuner's compiler and optimization infrastructure.

What you will be doing

  • Evaluate inference frameworks and serving systems, select the right components, and define how they integrate into Daisytuner's optimization platform.
  • Design scalable inference architectures, covering model serving, request scheduling, batching, resource allocation, GPU utilization and distributed inference.
  • Design and build distributed workload execution across heterogeneous compute environments, including scheduling, orchestration, resource management and failure recovery.
  • Define the interfaces between inference services, distributed execution, the compiler and the application platform.
  • Work with compiler engineers to integrate inference technologies with Daisytuner's compiler and optimization infrastructure.
  • Work with Full Stack developers and DevOps engineers on application integration, deployment, observability, operational reliability and processing performance data at scale.
  • Follow emerging technologies and shape the technical roadmap for inference and distributed execution.

What you are bringing

  • MSc in Computer Science, Software Engineering, Distributed Systems or a related field, or equivalent practical experience.
  • 5+ years of professional experience in backend engineering, distributed systems or systems software.
  • Experience designing, building and operating distributed or data-intensive production systems, including asynchronous execution, scheduling and resource management.
  • A solid understanding of LLM inference architectures and the challenges of deploying and scaling inference workloads.
  • Proficiency in at least one relevant programming language, such as Go, Python, C++ or Rust.
  • Experience taking technical ownership of complex systems: making architecture decisions, weighing trade-offs, and integrating different services and technologies into a reliable solution.

Nice to have

  • Hands-on experience with production AI inference, LLM serving or ML infrastructure.
  • Experience with LLM inference frameworks and serving systems such as vLLM, SGLang or Triton Inference Server.
  • Experience with distributed inference, including tensor parallelism, pipeline parallelism or multi-node inference.
  • Experience deploying AI workloads in on-premise or enterprise environments.
  • Experience with GPU and heterogeneous compute environments.
  • Experience with Kubernetes, Slurm, Ray or other workload and cluster schedulers.
  • Experience with distributed or analytical databases, or systems that process high volumes of performance data.
  • Familiarity with CUDA, ROCm or other accelerator programming environments.
  • Experience integrating native C/C++ components into larger software systems.

What we offer

  • A small, highly technical team where your work directly shapes our core technology.
  • Ownership of Daisytuner's inference and distributed execution architecture, from technology choices to production.
  • The opportunity to work at the intersection of compilers, machine learning and high-performance computing.
  • Real-world deployments on heterogeneous hardware in customer environments.
  • Competitive compensation and potential equity participation.

How to apply

Please send your application to recruiting@daisytuner.com. Include your CV, a few sentences on why this role interests you and your earliest possible start date. Links to GitHub, publications or projects you've worked on are welcome.

We welcome applications from people of all backgrounds and do not discriminate on the basis of gender, ethnic origin, nationality, religion or belief, disability, age or sexual identity.