The Sr. Machine Learning Engineer is responsible for designing, building, and deploying machine learning systems that power AI-driven features across Mirion's products. This role combines hands-on modeling and ML infrastructure work with technical leadership — driving best practices for the ML lifecycle, mentoring engineers, and partnering with stakeholders to translate business problems into production-grade ML solutions.

Responsibilities

Design, train, and deploy machine learning models for applied use cases across radiation safety, nuclear energy, and nuclear medicine. Architect end-to-end ML systems, including training pipelines, model serving infrastructure, and monitoring. Lead technical design reviews and mentor junior ML engineers on modeling, MLOps, and architectural best practices. Establish standards for model evaluation, experiment tracking, reproducibility, and responsible AI across the team. Partner with the Data Platform team to define feature requirements and ensure ML workloads are well-supported by the underlying data infrastructure. Collaborate with stakeholders and product partners to translate business problems into well-scoped ML solutions. Drive optimization initiatives for model performance, inference cost, and reliability in production. Participate in hiring and team building for the Applied AI function. Contribute to architectural decisions and long-term ML strategy. Troubleshoot production model issues — drift, degradation, and pipeline failures — and implement robust monitoring and alerting. Minimum Qualifications 5+ years experience in machine learning engineering, applied ML, or related field. Strong proficiency in Python and modern ML frameworks (PyTorch, TensorFlow, or similar). Deep experience taking ML models from research/prototype through to production deployment. Hands-on experience with ML infrastructure — training pipelines, model serving, experiment tracking, and monitoring. Solid software engineering fundamentals: testing, code review, version control, and CI/CD. Working knowledge of SQL and modern data warehouses or lakehouses (Snowflake, BigQuery, Databricks, etc.). Experience with cloud platforms (AWS, GCP, or Azure) at scale. Proven ability to mentor and guide junior engineers.

Preferred Qualifications

Experience building applied AI products or ML platforms from the ground up. Experience with Databricks, MLflow, and lakehouse-based ML workflows. Expertise with LLMs, RAG systems, or generative AI applications in production. Experience with feature stores, vector databases, and real-time inference architectures. Knowledge of model governance, model lineage, and responsible AI practices. Background in regulatory-heavy industries or complex compliance requirements. Experience with infrastructure-as-code and MLOps practices. Background in computer vision, time-series, or signal processing (relevant to radiation detection data).