Senior Software Engineer AI Infrastructure

📋 Description

• • Kraken is at the forefront of the cryptocurrency revolution, driven by a mission to accelerate global adoption and empower individuals with financial freedom and inclusion. We are a globally distributed team of passionate "Krakenites" united by our conviction in crypto and our desire to unlock its transformative potential. Our culture is deeply rooted in crypto values, and we pride ourselves on attracting and retaining some of the most talented minds in the industry. We encourage all prospective candidates to immerse themselves in our Kraken Culture page to understand our ethos, values, and mission, and to familiarize themselves with the Kraken app by creating an account.
• • As a fully remote company, Krakenites thrive in over 70 countries, speaking more than 50 languages. We are pioneers in developing premium crypto products for a diverse user base, from seasoned traders and institutions to newcomers entering the space. Our commitment to industry-leading security, comprehensive crypto education, and unparalleled client support is evident across our product suite, including Kraken Pro, Desktop, Wallet, and Kraken Futures.
• • The AI Infrastructure team plays a pivotal role in building and operating the production systems that power intelligent agents at scale. This team forms the bedrock of our agent platform, ensuring that the critical layers for model inference, orchestration, and execution are not only reliable and observable but also exceptionally performant under demanding real-world loads. We operate in a high-scale, high-stakes environment where our systems serve millions of users and must adhere to stringent standards for reliability, latency, and correctness.
• • In this role, you will be instrumental in designing and constructing the foundational infrastructure layer that underpins our AI agent systems in production. This involves developing high-performance services, primarily using Rust, that are responsible for the intricate processes of model inference, orchestration, and execution. You will architect scalable systems engineered to support millions of users and handle exceptionally high request throughput, ensuring our platform can grow and adapt to future demands.
• • A key aspect of this position is building robust and reliable Machine Learning Infrastructure (MLOps) patterns. This includes establishing best practices for model deployment, rigorous evaluation, and continuous monitoring to ensure the quality and effectiveness of our AI models. You will also be responsible for defining critical guardrails, implementing comprehensive observability solutions, and designing sophisticated failure handling mechanisms for agent-driven workflows, ensuring the safety and stability of our AI operations.
• • Your responsibilities will extend to optimizing critical performance metrics such as latency, throughput, and cost-effectiveness across both inference and orchestration layers. This requires a deep understanding of system performance and a proactive approach to identifying and implementing improvements. You will collaborate closely with the Agent Systems team, translating cutting-edge experimental prototypes into hardened, production-ready systems that can be deployed with confidence.
• • This is a unique opportunity to contribute to foundational infrastructure decisions within a high-scale, high-impact environment. You will be empowered to take high ownership in a deeply production-oriented team, where your systems thinking and applied ML infrastructure experience will be crucial. The work involves building in Rust and operating services where performance and understanding failure modes are paramount. You will be a key player in shaping the future of AI at Kraken, ensuring our intelligent agents operate seamlessly and effectively at scale.
• • We are looking for engineers who possess a strong systems-level programming background and a deep understanding of distributed systems principles. Your experience in reliability engineering and performance optimization will be vital. If you are passionate about building resilient, high-performance infrastructure and thrive in a challenging, production-focused environment, this role offers an unparalleled opportunity to make a significant impact.