Data Scientist

Dynamic Risk is a widely recognized integrity, risk management and software solutions company within the energy sector. We've been delivering our expertise and solutions since 1996 and we've become the industry-leading provider of pipeline integrity management solutions, which includes our suit of IRAS Software Applications.

Purpose
The goal of the IMP, Data Science Advisor is to be at the forefront of innovation, helping customers leverage and mine their pipeline integrity data to optimize their overall integrity management program, including ILI analysis, threat assessment, risk management, and spend optimization. This role will help shape and execute our data science strategy by applying advanced analytics, machine learning, and AI techniques to solve real-world problems in the energy and infrastructure sectors for predictive and diagnostic capabilities.

This is a proactive, high-impact, customer-facing role suited for a passionate individual who thrives on curiosity, problem-solving, and driving measurable results through data. This role will work closely with clients, product teams, and developers to transform large and complex datasets into meaningful business insights.

Responsibilities

• Conduct data science problem discovery workshops with customers and translate them into machine learning solutions using traditional, generative, and agentic AI approaches. Apply data mining, data modeling, natural language processing, and statistical techniques to extract insights. Building cloud-based predictive and prescriptive insights to customer problems through data mining/analysis, ML/AI tools and algorithms. Translate the complex analytics into simple, actionable visual insights using tools such as Tableau, PowerBI, and Jupyter. Communicate results clearly to both technical and non-technical stakeholders.
• Serve as a liaison between clients and software developers to ensure alignment between data insights and product functionality. Configure and support the productization deployment of analytical components into Dynamic Risk's software platform. Support the product development team in leveraging data science methodologies and algorithms for master data management.
• Envision the bigger picture to build scalable, maintainable analytics systems, leveraging ML (machine learning) platforms, tools, and frameworks to implement predictive analytics for pipeline integrity, asset health, and risk forecasting for very large data sets (e.g. Databricks, Spark, Azure ML, TensorFlow, Hadoop.)
• Participate in industry events and conferences; contribute to the development of white papers and other thought leadership materials.
• Work closely with the Software Product Manager to develop and prioritize customer specific data science solutions for productization based on market and customer need.
• Act as a support agent to the engineering consulting and sales teams by engaging with customers as a data science subject matter expert, identifying client challenges & opportunities (product and services) for integrity management.
• Lead technical documentation efforts including data mapping, analytics configurations, and user documentation. Deliver client training sessions and provide post-deployment support as needed.
• Develop and lead internal and customer-facing demonstrations, collecting feedback to iterate with the Development team on ML based product design.

Experience/Education

• Bachelor's degree in Data Science, Statistics, Mathematics, Computer Science, or a related field is required.
• Minimum of 5 years of practical experience in data analytics, machine learning, or a similar field.
• Experience in pipeline or pipeline integrity domain is a strong asset.
• Proficient in Python and SQL (T-SQL, pgSQL, PL/pgSQL).
• C# experience is an asset.
• Strong knowledge and expertise of statistical analysis, algorithms, and ML techniques (e.g., classification?, regression, boosting, forests, text mining) including newer technologies such as Generative and Agentic AI.
• Experience with cloud platforms such as Azure, AWS, or GCP.
• Familiarity with data infrastructures including data warehouses, datamarts, and data lakes.
• Strong presentation and storytelling skills with a customer-focused mindset.

Software

• Experience with cloud and big data tools (e.g., TensorFlow, Azure ML)
• Hands-on with data manipulation tools, frameworks, and platforms (e.g., BigQuery, Snowflake, Databricks, Spark, Hadoop, SQL, panadas, NumPy, PowerBI, Tableau, Azure ML)
• Proven experience with Python
• Familiarity with DevOps and project management tools such as Azure DevOps and Jira