Lead Software Engineer, Runtime

Lead Software Engineer, Runtime Mistral AI About Mistral At Mistral AI, we believe in the power of AI to simplify tasks, save time and enhance learning and creativity. Our technology is designed to integrate seamlessly into daily working life. We democratize AI through high-performance, optimized, open-source and cutting-edge models, products and solutions. Our comprehensive AI platform is designed to meet enterprise needs, whether on‑premises or in cloud environments. Our offerings include le Chat, the AI assistant for life and work. We are a dynamic, collaborative team passionate about AI and its potential to transform society. Our diverse workforce thrives in competitive environments and is committed to driving innovation. Teams are distributed across France, USA, UK, Germany and Singapore. We are creative, low‑ego and team‑spirited. Join us to be part of a pioneering company shaping the future of AI. See more about our culture on https://mistral.ai/careers. Role summary As the Technical Lead for the Inference team, you will drive the architecture and optimization of our inference backbone, ensuring high performance, scalability, and efficiency in a dynamic environment. You will lead the acquisition and automation of benchmarks, collaborate with cross‑functional teams, and innovate solutions to enhance our AI‑powered applications. What you will do Architect and optimize the inference for high‑volume, low‑latency, and high‑availability environments Lead the acquisition and automation of benchmarks at both micro and macro scales Introduce new techniques and tools to improve performance, latency, throughput, and efficiency in our model inference stack Build tools to identify bottlenecks and sources of instability, and design solutions to address them Collaborate with machine learning researchers, engineers, and product managers to bring cutting‑edge technologies into production Optimize code and infrastructure to maximize hardware utilization and efficiency Mentor and guide team members, fostering a culture of collaboration, innovation, and continuous learning About You Extensive experience in C++ and Python, with a strong focus on backend development and performance optimization Deep understanding of modern ML architectures and experience with performance optimization for inference Proven track record with large‑scale distributed systems, particularly performance‑critical ones Familiarity with PyTorch, TensorRT, CUDA, NCCL Strong grasp of infrastructure, continuous integration, and continuous development principles Ability to lead and mentor team members, driving projects from concept to implementation Results‑oriented mindset with a bias towards flexibility and impact Passion for staying ahead of emerging technologies and applying them to AI‑driven solutions Humble attitude, eagerness to help colleagues, and a desire to see the team succeed Our Culture Reason with rigor Are you audacious enough? Make our customers succeed Ship early and accelerate Leave your ego aside Location & Remote This role is based in one of our European offices (Paris, France and London, UK). We will only consider candidates who either reside or are open to relocating there. We strongly believe in the value of in‑person collaboration and encourage going to the office as much as we can (at least 3 days per week) to create bonds and smooth communication. Our remote policy aims to provide flexibility, improve work‑life balance and increase productivity. What we offer Competitive salary and equity (stock‑options) Health insurance Transportation allowance Sport allowance Meal vouchers Private pension plan Generous parental leave policy Visa sponsorship We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us. #J-18808-Ljbffr