PhD Data Scientist

Data Scientist (PhD, Chemical Engineering, Process Engineering & Machine Learning)

Start date
:
To be agreed.
Duration & hours
:
Full-time permanent contract, 40 hours per week.
Salary
:
Competitive up to £42k.

Workplace
:
Currently hybrid working pattern of two days in the office in Altrincham, Cheshire, followed by three days home working.

Travel Required
:
There is no immediate requirement for business travel, but you must be open to travel on an ad hoc basis to meet business demands.

The company
:
Process Integration Limited (PIL) is a visionary technology company dedicated to delivering integrated first principle and AI-driven solutions for the oil and gas industry. Our state-of-the-art, closed-loop products seamlessly merge digital twins, comprehensive optimisation, and smart execution systems while promoting operational excellence. We are committed to providing exceptional value to clients by pushing the boundaries of innovation, driving sustainable progress, and shaping the future of the energy sector through advanced technology.

We are looking for a highly skilled and innovative Data Scientist with a PhD in Chemical Engineering with a focus
on full integration of domain-specific process knowledge into machine learning models. As a Data Scientist, you
will play a pivotal role in advancing our chemical processes, optimising process performance, and driving
product development. Your expertise in chemical engineering, machine learning, and mathematical
modelling will be instrumental in shaping our future.

Qualifications & Skills

• PhD or equivalent advanced degree in Chemical Engineering, with a strong focus on data analysis, statistical
  modelling, and computational techniques.
• Proficiency in Python for data analysis and machine learning. Strong understanding of statistical methods,
  data manipulation, and data visualisation libraries (e.g., pandas and Num Py, scikit-learn, PyTorch,
  matplotlib/plotly).
• Utilise process/data analysis techniques to assess the potential of existing processes and propose alternative
  production methods and operating parameters to improve process performance.
• Strong analytical and problem-solving skills to tackle complex challenges related to chemical processes and
  data analysis, particularly from a data science and machine learning point of view. Ability to break down
  problems into manageable components and develop innovative solutions using data-driven approaches.
• Understanding and hands-on experience in solving complex data-oriented issues, often requiring literature
  research.
• Modelling and optimisation of refinery, petrochemical, and chemical processes.
• Understanding of mathematical modelling and optimisation approaches for engineering purposes (particularly
  non-linear oil and gas processes).
• Willingness to engage in continuous learning and professional development activities to enhance skills and
  expertise.
• Attention to Detail:
  Meticulous attention to detail to ensure accuracy and reliability of data analysis and
  modelling results. Ability to identify and address potential sources of error or bias in data and methodologies.
• Excellent critical thinking skills and a passion for innovation.
• Effective communication and teamwork abilities.
• Strong background in machine learning, including experience with deep learning, regression, and data-driven
  modelling.

Responsibilities:

• Develop predictive models using a variety of techniques including traditional statistical methods, machine learning, LLMs/RAG/Agents.
• Ensure these models are not only technically competent but also fully integrated with domain-specific process knowledge to enhance performance and application.
• Focus on the readiness of models for practical implementation in client-specific environments, ensuring they are robust, scalable, and adaptable.

Process-Oriented Data Strategy:

• Design and implement data collection and analysis strategies that leverage deep process understanding to optimise the accuracy and utility of models.
• This involves selecting the right type of data, pre-processing methods, and data enrichment techniques that reflect process intricacies.
• Ensure these strategies are conducive to real-world applications, particularly in preparing models for integration into client projects.
• Innovate and develop in-house tools and software solutions that facilitate the modelling, simulation, and analysis of complex chemical processes.
• These tools should support the seamless integration of new AI technologies and process engineering principles.
• Design these tools to be flexible and effective in deploying developed models into client systems, enhancing the operational impact.

Stakeholder Engagement and Solution Implementation:

• Work directly with colleagues in technical and business teams to translate complex model outputs into actionable business insights.
• Present findings in a way that is accessible to non-experts and can influence strategic decisions.

Continuous Learning and Skill Enhancement:

• Keep abreast of the latest developments in data science, AI, and chemical…