Responsibilities:
Data cleaning, preparation, and feature engineering
- Clean, preprocess, and transform large and diverse datasets from various sources
- Engineer relevant features to improve model accuracy and interpretability
Model building and evaluation
- Develop and refine machine learning models (e.g., time series forecasting, regression, classification) using Python and relevant libraries (e.g., TensorFlow, PyTorch, Scikit-learn)
- Incorporate domain knowledge from chemistry, physics, and hydraulics into model development
- Experiment with different model architectures and hyperparameters to optimize performance
Model deployment, optimization, monitoring, and lifecycle management
- Deploy models to Azure cloud platform using appropriate tools and techniques
- Monitor model performance in production and identify areas for improvement
Collaborate with cross-functional teams
- Support client success to generate statistical analysis and reports
- Support development teams to understand business requirements and translate them into technical solutions
- Communicate complex technical concepts effectively to both technical and non-technical audiences
Qualifications:
- Strong proficiency in Python programming and machine learning (Numpy, Pandas, TensorFlow, Scikit-learn), as well as proficiency in writing code to be scalable, secure, well documented, and efficient.
- Strong knowledge and experience in data preprocessing, feature engineering, and model evaluation.
- Solid understanding of machine learning algorithms and techniques (e.g., time series forecasting, regression, classification).
- Self-motivated to work independently, prioritize tasks, and meet deadlines with limited supervision.
- Persistent and passionate about problem-solving with strong analytical skills.
- Strong communication and collaboration skills.
- Cultural qualification: We are seeking to build an A.O.R.T.I.C. culture at the heart of our company. The core values we seek in every individual are the following:
Advancement
We strive to advance Fontus Blue’s company mission and technology through learning and growing as individuals and team members.
Ownership
We take full responsibility for our actions, decisions, and the outcomes they produce, empowering every team member to lead with accountability and integrity.
Respectful
We demonstrate openness to differing views and opinions, we show up on time, and we speak with care and curiosity.
Tenacity
We adapt and are persistent, energized by our passion for life and water.
Inclusive
We are dedicated to learning how to cultivate a welcoming professional environment for every person.
Collaborative
We are team players who support each other and work together.
Preferred Qualifications:
- 1-2 years of experience in data science, machine learning, or a related field.
- Familiarity with water treatment processes and relevant scientific principles, or experience working within the water industry.
- Experience with Microsoft Azure (Webapps, function apps… etc.).
- Proficient in using Git for version control, including branching, merging, and managing code repositories.
- Experience or interest in developing AI-driven solutions, particularly focused on natural language processing (NLP) and language learning models (LLM).
Position Overview:
Reports to: Product Manager
Employment Status: Full time Exempt
Location: Remote (U.S), preferred location is Ohio. If you don’t live in the Eastern Time Zone, this position will require some flexibility to participate in meetings during core business hours in the EST.
Must be open to traveling one to two times per year for team working summits in-person.
Must have dependable high-speed wifi and a work space conducive to focused working. Fontus will provide a laptop or reimbursement for up to $1,700 to purchase a computer.
This position is expected to start in January 2025.
