Detection Data Scientist - Real-World Signals (Hybrid) in Oxford

Detection Data Scientist - Real-World Signals (Hybrid) in Oxford

Oxford Full-Time 50000 - 70000 Β£ / year (est.) No working from home possible
Physics World

At a Glance

  • Tasks: Build detection models using real sensor data and machine learning techniques.
  • Company: Oxford Dynamics, a leader in innovative data solutions.
  • Benefits: Hybrid work model, meaningful ownership, and competitive salary.
  • Other info: Collaborative environment with opportunities for professional growth.
  • Why this job: Make a real impact by working with cutting-edge technology and data.
  • Qualifications: Experience in data science and familiarity with machine learning methods.

The predicted salary is between 50000 - 70000 Β£ per year.

Oxford Dynamics is seeking an applied data scientist to build detection on real sensor data, balancing machine learning with deterministic methods.

You will select techniques, develop features from AIS and RF signals, and own end-to-end evaluation and model drift governance.

You will work closely with engineers and analysts, integrating data from geospatial platforms like Arc GIS and Palantir Foundry. Hybrid work and meaningful ownership are offered.

#J-18808-Ljbffr

Detection Data Scientist - Real-World Signals (Hybrid) in Oxford employer: Physics World

Physics World is an excellent employer, offering a supportive work culture that values collaboration and innovation within the Science Department. Employees benefit from a comprehensive pension scheme, nutritious meals in the Dining Hall, and access to outstanding facilities such as gyms and pools, all while contributing to meaningful educational experiences in a vibrant academic environment.

Physics World

Contact Details:

Physics World Recruitment Team

We think you need these skills to ace Detection Data Scientist - Real-World Signals (Hybrid) in Oxford

Machine Learning
Deterministic Methods
Feature Development
AIS Signal Processing
RF Signal Processing
Model Evaluation
Model Drift Governance