Senior Applied Scientist - Computer Vision for Quantum

Microsoft Microsoft · Big Tech · Lyngby, Denmark · Quantum Software Engineering

Senior Applied Scientist role focused on building and scaling analytical pipelines and AI/ML models for experimental microscopy imaging and characterization data in the quantum computing domain. The role involves developing agentic workflows, image analysis algorithms, and ensuring the robustness and reliability of production-grade analysis systems to provide actionable insights for engineering teams.

What you'd actually do

  1. Develop and maintain scalable analysis pipelines and agentic workflows for experimental microscopy imaging and characterization data, enabling consistent and reliable interpretation of the data.
  2. Design and implement algorithms for image analysis, registration, feature extraction, and quantitative metrics, ensuring robustness, correctness, and reproducibility in production environments.
  3. Build and operationalize machine learning and AI models for feature extraction, classification, regression, or anomaly detection, ensuring interpretability, validation, and long-term reliability.
  4. Partner with physicists, hardware engineers, materials scientists, and data engineering teams to translate experimental data into actionable insights that improve product quality and yield.
  5. Design and maintain clear, interpretable data models and datasets, including handling of missing, invalid, and unprocessed data states to ensure reproducibility.

Skills

Required

  • Python programming
  • scientific computing
  • development of production-quality code
  • image processing
  • computer vision
  • imaging-based analysis workflows
  • statistical analysis
  • uncertainty estimation in measurement or experimental systems

Nice to have

  • developing, training, validating, and deploying machine learning models for experimental or production data
  • building and maintaining data pipelines in modern distributed or analytics environments (e.g., Spark, Databricks, Delta Lake, or equivalent)
  • nanofabrication processes and associated metrology techniques
  • working in shared, long-lived analytical or production codebases
  • collaborating with experimental, hardware, or scientific teams and reasoning about physical system constraints

What the JD emphasized

  • production-quality code
  • production environments
  • production-grade analysis workflows
  • production systems
  • production data
  • production environments

Other signals

  • AI/ML models for feature extraction, classification, regression, or anomaly detection
  • agentic workflows for experimental microscopy imaging and characterization data
  • scalable analysis pipelines