Performance Engineer (Containers/Serverless)

Location: Helsinki, Finland; hybrid work with presence in the Helsinki office at least 3 days per week

Company

hirify.global builds cloud infrastructure for AI, operating GPU clusters across Europe, the US, and Asia for demanding production ML workloads.

What you will do

• Profile and optimize the end-to-end execution path for containerized ML/AI workloads, including image distribution, runtime startup, weight loading, and inference.
• Design and tune storage layers between S3-compatible object stores and GPU nodes, including prefetchers, caching tiers, network filesystems, and local NVMe layouts.
• Improve time-to-first-token, training step time, inference throughput, and cold-start latency for internal and customer workloads.
• Benchmark real workloads and translate findings into measurable platform improvements.
• Collaborate across compute, networking, and platform teams to remove end-to-end bottlenecks.
• Document performance findings and trade-offs in internal and occasional external technical write-ups.

Requirements

• Production experience making ML/AI workloads measurably faster.
• Strong knowledge of Linux storage and container runtime internals.
• Hands-on experience with at least one distributed or network filesystem and S3-compatible object storage.
• Experience with object-storage performance issues such as small-object overhead, range requests, eventual consistency, and multipart tuning.
• Familiarity with model-serving runtimes such as vLLM or SGLang and formats including safetensors, GGUF, and sharded checkpoints.
• Ability to reason across NICs, switches, filesystems, caches, container runtimes, and GPUs as one system.

Nice to have

• Systems programming experience with Go, Rust, or Python.
• Experience with checkpoint/restore, container image acceleration, caching layers, RDMA, GPUDirect Storage, or NVMe-oF.
• Experience with serverless GPU platforms, model registries, or Kubernetes-based ML infrastructure.
• Open-source contributions to storage, ML runtime, container, or kernel projects.
• Bare-metal performance engineering experience.

Culture & Benefits

• Full-time, permanent employment.
• Cash and equity compensation.
• Healthcare, lunch, wellbeing, and other fringe benefits.
• Access to real GPUs for performance testing.
• Low-hierarchy environment with pragmatic delivery and engineering ownership.