About the job
At Crusoe, we are on a mission to revolutionize energy and intelligence accessibility. Our vision is to create a world where ambition meets innovation through AI, all while upholding principles of scale, speed, and sustainability.
Join us in leading the AI revolution with eco-friendly technology at Crusoe. As part of our dynamic team, you will spearhead significant innovation, make a real difference, and contribute to the development of cutting-edge cloud infrastructure that prioritizes responsibility and transformation.
Role Overview:
We are seeking a Research Engineer who will be instrumental in designing, assessing, and implementing next-generation AI inference systems. This position bridges the gap between applied research and practical deployment, focusing on enhancing the performance, efficiency, reliability, and cost-effectiveness of large-scale inference workloads.
You will collaborate closely with systems engineers, ML engineers, and infrastructure teams to translate innovative research concepts into impactful real-world applications.
Key Responsibilities:
Research, implement, and assess state-of-the-art AI inference techniques, including speculative decoding, prefill–decode disaggregation, quantization, and kernel-level optimizations, with a keen focus on real-world applications.
Design and execute experiments to analyze trade-offs in latency, throughput, cost, and quality, utilizing these insights for informed system and model designs.
Develop and refine high-performance inference prototypes, translating research ideas into practical applications while optimizing performance-critical kernels and enhancing execution efficiency on modern accelerators.
Examine real-world inference workloads to identify efficiency and scalability improvement opportunities, staying informed on advancements in ML systems and inference research, and sharing findings through internal reports and external contributions.
Contribute to and define the company’s roadmap, directly influencing product development and customer satisfaction.
What You Bring:
A strong foundation in computer science, machine learning, or systems research.
Adeptness in evaluating performance at scale while navigating real-world constraints.
Proficiency in programming and algorithm development for efficient execution.
Excellent collaborative skills to work effectively with cross-functional teams.

