AI Trace Generation Engineer

Your mission

• Design and implement a trace collection system for distributed LLM workloads, capturing compute operations, communication primitives, memory usage, and cluster topology across multi-GPU and multi-node setups
• Validate that collected traces accurately reflect real workload behavior - verifying operation completeness, timing consistency, and data integrity across inference and training pipelines
• Integrate with and instrument major LLM frameworks (vLLM, TensorRT-LLM, DeepSpeed, Megatron-LM and others) to extract meaningful execution data without disrupting performance
• Use collected traces as input to discrete event simulations that model and replay distributed AI workload behavior at scale
• Analyze trace data to surface bottlenecks and inefficiencies across the stack, from individual kernel execution to cluster-wide communication patterns

Your profile

• 3+ years of experience in AI systems, ML infrastructure , or a closely related area
• Hands‑on experience with at least one major LLM serving or training framework
• Strong proficiency in Python and C++ , with a solid understanding of GPU architecture, memory bandwidth, and the difference between compute‑bound and memory‑bound operations
• Solid understanding of distributed communication
• Familiarity with parallelism strategies and how they shape execution behavior across large clusters
• Open source contributions or published research in relevant areas will definitely be appreciated!
• Previous startup experience is a plus - we move fast and value people who are comfortable with that

Why us?

• Build something big: Help build and scale a fast‑growing AI infrastructure startup
• Pay & perks: Competitive compensation with a performance‑based incentive, subsidized Deutschlandticket, and access to a discount portal
• Work your way: Flexible hours with hybrid and remote‑friendly options
• Fast lanes, no red tape: Flat hierarchies and rapid decision‑making mean ideas ship quickly
• Global team: Work with a diverse, international team across Germany and the USA
• Modern headquarters: Well‑stocked office near the Heidelberg Hauptbahnhof, available on a hybrid basis or as a place to connect during our quarterly team workshops
• Top setup: Your choice of high‑quality hardware and equipment
• Relocation support: We’ll help make your move to join us as smooth as possible