Senior Software Engineer – AI Infrastructure

Kraken's AI Infrastructure team builds and runs the production systems behind the company's intelligent agents. Working alongside the Agent Systems team, you will create the core primitives that let agents operate safely across internal systems, in a high-scale environment serving millions of users and built mainly in Rust.

• Design and build the infrastructure layer for AI agent systems in production.
• Develop high-performance Rust services for model inference, orchestration, and execution.
• Build ML infrastructure and MLOps patterns for deployment, evaluation, and monitoring.
• Define guardrails, observability, and failure handling for agent-driven workflows.
• Optimize latency, throughput, and cost across inference and orchestration layers.
• Work with Agent Systems to turn prototypes into hardened production systems.

• 5+ years building and operating high-scale production systems.
• Strong Rust and systems-level programming skills.
• Deep understanding of distributed systems, reliability engineering, and performance optimization.
• Familiarity with ML infrastructure, model serving, or MLOps.
• Experience designing observability, monitoring, and failure recovery systems.

Nice to have: experience building infrastructure for agent-based or LLM-powered systems, high-performance networking and low-latency architectures, container orchestration and cloud-native infrastructure, evaluation frameworks and model performance monitoring, and 0-to-1 or platform-building teams. Remote role; secondary hiring locations include Brazil, Ireland, Peru, Canada, Poland, Spain and others.