Principal Data Scientist - Simulation & Techno-Economic Optimisation at Fortescue Metals Group
Perth, Western Australia, Australia -
Full Time


Start Date

Immediate

Expiry Date

05 Dec, 25

Salary

0.0

Posted On

06 Sep, 25

Experience

8 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

No

Skills

Python, Applied Mathematics, C++, Renewable Energy Systems, Aws, Techno Economic Analysis, Data Integration, Communication Skills, Energy Systems, Collaboration, Data Science, Machine Learning, Hydrogen

Industry

Information Technology/IT

Description

ABOUT US

Fortescue is both a proud West Australian company and a global green solutions business. We are recognised for our culture, innovation and industry-leading development of infrastructure, mining assets and green energy initiatives.

QUALIFICATIONS AND EXPERIENCE

  • PhD or Master’s degree in Data Science, Engineering, Applied Mathematics, Energy Systems, or a related field
  • 8+ years of experience in advanced data science, machine learning, or computational modelling, ideally in energy, resources, or process industries
  • Proven expertise in simulation-based optimisation, surrogate modelling, and large-scale data integration
  • Strong proficiency in C++, Python strongly preferred
  • Strong experience with ML frameworks (e.g., TensorFlow, PyTorch, scikit-learn, OpenAI).
  • Familiarity with AWS desired
  • Demonstrated experience linking engineering/physical models with techno-economic analysis.
  • Familiarity with renewable energy systems, hydrogen, or metallurgical processes (advantageous).
  • Excellent leadership, collaboration, and communication skills, with the ability to influence and align diverse stakeholders.
Responsibilities
  • Lead development of advanced simulation and ML-driven frameworks for renewable energy and green iron
  • Mentor and guide teams in modelling, data quality, and uncertainty management
  • Translate technical insights into clear recommendations for senior leaders
  • Create hybrid models combining simulation, optimisation, and machine learning
  • Apply ML to speed up simulations, identify cost drivers, and optimise systems
  • Build models linking renewable energy, hydrogen, electrolysers, and green iron production
  • Integrate engineering, cost, and financial data into unified decision-support tools
  • Run scenario analyses and sensitivity studies to guide investment and delivery
  • Drive innovation with digital twins, surrogate models, reinforcement learning, and partnerships
  • Collaborate across teams, promoting transparency and communicating results effectively.
Loading...