DescriptionWe are looking for a Machine Learning Engineer to design, build, and deploy machine learning systems that improve the calibration, control, and operation of quantum processors. In this role, you will work at the intersection of machine learning, quantum physics, and software engineering, translating noisy, non-stationary, safety-critical control problems into ML solutions that run on real hardware in production labs.
You will develop reinforcement learning policies, Bayesian inference methods, and agentic frameworks that make quantum control more autonomous, more sample-efficient, and more robust to drift. This position offers unprecedented exposure to diverse qubit types and quantum architectures, with a tight feedback loop between your models and the systems they steer, and the opportunity to deliver groundbreaking ML-driven solutions to the labs and companies defining the next generation of quantum systems.
Responsibilities:- Develop reinforcement learning, Bayesian inference, and probabilistic modelling approaches for parameter tuning, drift tracking, and adaptive measurement, to be deployed on real hardware.
- Develop real-time parameter steering for calibration during QEC and between circuits.
- Develop and maintain agentic frameworks for autonomous system control and calibration.
- Develop and maintain Python-based ML services and libraries that integrate with the wider Quantum Machines control stack, including QUA, Qualibrate, and the OPX1000.
- Work directly with customers and partner labs to deploy, validate, and iterate on ML solutions in real experimental environments.
- Collaborate cross-functionally with product, R&D, and hardware teams, contributing to internal libraries, customer-facing SDKs, and training materials.
Requirements- PhD/Master in Machine Learning, Physics, Applied Physics, Quantum Information Science, or a related field. 4+ years of relevant experience
- Strong background in Machine Learning and Deep Learning, with hands-on experience in at least one of: deep learning, reinforcement learning, agentic AI
- Strong Python proficiency, including scientific or systems-oriented codebases
- Solid software engineering fundamentals (architecture, Git workflows, testing, code review)
- Proven track record of taking ML from prototype to deployment under real-world constraints - non-stationary data, expensive evaluations, or safety-critical action spaces. Robotics, online control, autonomous vehicles, or hardware-in-the-loop ML all transfer well
- Strong problem-solving skills and customer-focused mindset; ability to work independently and in multidisciplinary teams
- Proven software development track record and excellent technical communication skills
- Familiarity with quantum computing concepts - qubit calibration, randomized benchmarking, QEC, optimal control- advantage
- Experience with sim-to-real, multi-objective RL, or meta-learning- advantage
