Senior AI Compute Infrastructure Engineer

Overview

Join Kraken’s dedicated AI Compute and Infrastructure team to power next-gen AI workloads at scale. You will own GPU and accelerator clusters, shaping cost-efficient, production-grade infrastructure used by AI researchers and engineers. You’ll partner with ML researchers, platform engineers, and security teams to remove bottlenecks and improve reliability. This role offers high impact in a mission-driven, remote-friendly company building premier crypto products.

Responsibilities

• Own and operate GPU and accelerator clusters for training, inference, evaluation, and experimentation, including drivers, runtimes, kernels, device plugins, node configuration, scheduling primitives, and workload isolation
• Design infrastructure to run models locally on GPUs where strategic and economical, reducing external dependencies and compute costs
• Build and improve scheduling, orchestration, placement, quota management, and utilization systems across heterogeneous accelerators
• Optimize inference pipelines for latency, throughput, reliability, memory efficiency, and cost using frameworks like vLLM, Triton Inference Server, TensorRT
• Collaborate with ML engineers and researchers to remove bottlenecks in training, evaluation, deployment, and production debugging workflows
• Build observability for GPU utilization, memory pressure, queue depth, saturation, token throughput, request latency, and spend
• Drive reliability, incident response, alerting, runbooks, and post-incident improvements for always-on AI compute infrastructure
• Evaluate and integrate new hardware, cloud instances, accelerators, runtimes, schedulers, and serving frameworks as the landscape evolves
• Build tooling that makes GPU usage visible and approachable for internal teams
• Contribute to long-term architecture decisions balancing performance, cost, scalability, and safety
• Shape architecture decisions to balance performance, cost efficiency, scalability, operational simplicity, and production safety

Key requirements

• 5+ years of infrastructure engineering with GPU compute, ML infrastructure, distributed systems, HPC, or large-scale production platforms
• Hands-on experience operating GPU clusters or accelerator-backed infrastructure in production environments
• Strong systems engineering fundamentals across Linux, networking, storage, containers, Kubernetes, distributed runtimes, and production debugging
• Experience with ML serving frameworks such as vLLM, Triton Inference Server, TensorRT, TorchServe, KServe, Ray Serve, or equivalents
• Proficiency in Python for infrastructure automation and tooling
• Understanding of performance tradeoffs across batching, concurrency, memory usage, GPU utilization, model size, latency, throughput, availability, and cost
• Track record of optimizing compute costs while maintaining performance and reliability
• Experience building observable systems with metrics, logs, traces, dashboards, alerts, and incident workflows
• Comfortable in high-stakes, always-on environments with emphasis on uptime and reliability
• Clear communicator capable of explaining infrastructure tradeoffs to researchers, product teams, and leadership

• clear communicator
• collaboration with cross-functional teams
• operational discipline
• GPU compute
• ML infrastructure
• Linux, networking, storage, containers, Kubernetes

…