Machine Learning Engineer

My client is changing the way cities maintain their infrastructure by automating inspection processes and providing unmatched data insights. We are looking for a machine learning engineer to join our team who wants to work on our entire machine learning pipeline that helps my client deliver real-time insights to cities around the world and to ourselves.Preferred QualificationsA Master's or PhD in a quantitative field or equivalent work experience3+ years of experience building and deploying machine learning models and data products in production environmentsExperience delivering data products based on tabular and time series datasetsStrong knowledge of machine learning techniques and tools, with experience in both classical methods and modern approaches (gradient boosted trees, neural networks)Expert-level knowledge of statistics, both descriptive and inferential, with a strong foundation in Bayesian inference and probabilistic modeling techniquesSkilled practitioner of the Python data science stack (NumPy, SciPy, Pandas, Jupyter, etc.), along with strong SQL skillsData visualization experienceFocus on creating robust data pipelines and ensuring accurate results are deliveredStrong verbal and written skills, with the ability to convey complex data models to non-technical audiencesWillingness to learnDomain knowledge in infrastructure or asset management is a plusExperience with cloud-based distributed traininginference management and orchestrationFamiliarity with OLAP databases and real-time analyticsAbout the JobWe are looking for a machine learning engineer to help us evolve our insights beyond single inspections to entire asset systems. Machine learning is a rapidly evolving field, and working in AI requires constant learning and exploration. We need someone ready to dive into the messy jungle of real-world data, with all its noise, inconsistencies, and variation. You'll be working at the forefront of machine learning to solve novel problems and create robust production systems.Working alongside the AI and Product teams, you will:Collaborate to develop requirements and understand the problem domainCollect, clean, and pipeline data, creating and analyzing key featuresBuild and test machine learning modelsManage the ML pipelineParticipate in an agile development processHave the opportunity to work on the entire technology stackWhy Join?My client is applying AI to a massive infrastructure challenge. Most people aren't aware, but aging sewer infrastructure is leading to significant leaks and overflows, posing environmental and public health risks.We are revolutionizing this antiquated industry by automating the labor-intensive process of labeling cracks, roots, and grease in pipeline inspection videos.As a 5-year-old, Series B-funded startup with a large and growing client base, we are looking to expand our product offerings and continue their rapid growth.LocationThis is a hybrid position, with attendance expected in our Walnut Creek, CA office at least two days per week.Salary & PerksTools you need to get the job doneCompetitive salary and potential equity-based remunerationUnlimited PTOBudget for courses, books, and conferences - your development is important to usKeywords:AI, Machine Learning, Statistics, Time Series, Tabular Data, Python, SciPy, Data SciencePay range: $160,000 - $170,000 per year (Walnut Creek, CA)

Created: 2025-02-21