Mistral is seeking a Research Engineer for the Latency & Throughput team to push the frontier of LLM inference. You will explore speculative decoding, quantization, and KV compression, turning research ideas into production-ready improvements within our vLLM-based serving stack.
You will work closely with inference engineers and researchers, running rigorous experiments, and contributing to design choices that balance latency gains with model quality.
#J-18808-Ljbffr
Research Engineer: AI Inference & Latency employer: Mistral
Mistral is an exceptional employer that fosters a dynamic and collaborative work culture, where innovation thrives and diverse teams come together to tackle complex challenges in AI. As a Recruiting Operations Manager, you will benefit from a comprehensive package of perks tailored to support your well-being and professional growth, all while working in a company that values creativity and continuous improvement. With opportunities for meaningful contributions and a commitment to employee development, Mistral stands out as a rewarding place to advance your career in a rapidly evolving industry.
