Senior/Staff Data Scientist

Gridsight is a rapidly growing Grid/CleanTech startup on a mission to accelerate global electrification and decarbonisation. We are building a vertical SaaS platform for electricity utilities, enabling them to modernise grid operations and unlock transformational flexibility capabilities such as dynamic operating envelopes and flexible interconnections. Having recently raised our Series A funding from Airtree Ventures, Energy Transition Ventures and Area VC, we are poised for rapid growth and are seeking talented individuals to join us on our mission.

Design and develop software and data science tools for modelling usage and generation of electricity, enabling electrical utilities to manage the growth and operation of their distribution networks through advanced data analytics.

• Design, build, and maintain software products and data science models capable of simulating or predicting key components, properties and events of electricity grids, including individual connections to the grid such as power assets, commercial, industrial, agricultural and infrastructure projects
• Obtain data from disparate sources to inform and support modelling, by performing data discovery and/or developing automated retrieval pipelines as needed
• Ensure software and model capabilities, coverage and performance align with customer requirements, directly engaging with customers from time to time in order to do so
• Collaborate with Software Engineers, Data Engineers, and other Product teams to understand data science requirements and translate them into technical solutions
• Establish and follow data, scientific, MLOps and software engineering best practices including testing, validation, documentation, monitoring, version control and code reviews
• Contribute to data science strategy and architectural decisions

• Senior/staff level experience: 5+ years in data science roles with demonstrable impact
• Software engineering fundamentals: proficiency in Python or similar language, architecture, system design, version control, testing practices, code review, CI/CD
• Numerical modelling: mathematical modelling, numerical methods, applied statistics
• ML modelling: experience developing, training, testing and validating machine learning models, as well as deploying them to production
• Customer-facing experience: experience delivering software/data products to customers, and iterating based on their feedback.

• Experience building data products for customer consumption
• Experience in energy, utilities, or IoT/sensor data domains
• Experience with time-series data or operational analytics
• Experience with business process modelling
• Experience discovering and integrating diverse data sources into complex modelling pipelines, both ML and otherwise
• Experience designing and implementing agentic workflows
• Experience optimising Python workflows, e.g. via parallel/distributed solutions or development of interfaces to optimised lower-level libraries
• Experience working in remote or distributed teams
• Data governance or compliance experience in regulated industries

• Data exploration and cleaning
• Numerical analysis, numerical modelling, numerical programming
• Statistical modelling and metrics
• Machine learning model architectures and techniques for training, testing, validation and optimisation
• Scientific design of analysis and simulation strategies

• Version control workflows with git and branching strategies
• Testing practices — unit, integration, and data quality testing
• Code review and collaborative development
• CI/CD principles and deployment automation
• Refactoring and managing technical debt
• Software architecture and system design

• Python, or strong evidence of an ability to pick it up quickly
• Version control: git
• Machine learning frameworks: scikit-learn, pytorch, keras, tensorflow or similar
• Continuous integration / continuous delivery: GitHub Actions, Gitlab CI/CD, Jenkins, Circle CI or similar

• Data science model design, development and maintenance
• Ability to easily translate business logic and abstract concepts into concrete, quantitative modelling and constraint strategies  
• Software performance optimization, troubleshooting and debugging, particularly in the context of numerical software
• Ability to demonstrate good code hygiene in the context of numerical programming: precision, error accumulation, convergence, stability, testing, code clarity, maintainability and documentation.
• Technical communication: explaining analyses, modelling and results to varied audiences
• Collaboration with cross-functional stakeholders including data engineers, software engineers, product specialists, designers and domain experts

• Ownership mindset — accountable for performance of grid connection modelling capabilities
• Pragmatic — balances technical rigour with delivery realities
• Organised — keeps clear and detailed records of decisions made and work done; manages time effectively 
• Detail-oriented, proactive — catches edge cases, modelling and software issues before they impact users
• Solution focused — thrives on ambiguity as an opportunity to deliver clarity and solutions
• Customer focused — thinks about data consumers and designs systems that serve their needs effectively
• Collaborative — works effectively across disciplines and teams
• Growth-oriented — continuously learning and helping others develop
• Calm under pressure — navigates competing priorities and interpersonal challenges without losing focus

Locations: Sydney, Melbourne, Canberra, Wollongong - hybrid and remote available