Job description

Are you passionate about applying cutting-edge AI, big data, and computer vision to real-world challenges? Do you want your work to make a tangible, positive impact on millions of travelers? Then this position might be your perfect fit. San Francisco International Airport (SFO) is seeking, a Data Science Lead will be responsible for big data analytics from a data science and data engineering perspective providing expertise in data manipulation, visualization, building and optimizing classifiers using machine learning and deep learning-based techniques. The goal is to optimize the guest experience at SFO to reduce costs for the airport to run its operations and increase revenue. Apply now and elevate your career in a dynamic, fast-paced environment: https://careers.sf.gov/l?go=B6gTc1zP Why join us? At SFO, we’re not just moving people from point A to B — we’re reimagining the traveler experience with data. From reducing wait times and improving safety to optimizing operations and revenue, your work will help shape the future of one of the world’s leading airports. You are excited about this opportunity because you will: – Define the roadmap for integrating video analytics, structured and unstructured data, and Artificial Intelligence/Machine Learning (AI/ML) capabilities into business strategies. – Identify opportunities to leverage video data for insights, automation, and innovation. – Align data science initiatives with organizational goals, ensuring measurable business impact. – Lead the development of solutions for extracting insights from video, structured and unstructured data. – Research, prototype, and deploy advanced AI/ML models for structured (3rd Party applications, APIs, streaming data) and unstructured data(video/audio/other). Oversee model lifecycle management, from design to deployment and monitoring; ensure scalability, performance, and accuracy of AI/ML solutions – Work closely with Data Engineers, Architects and CI/CD Engineers to design data pipelines that handle structured and/or unstructured data efficiently. Implement real-time and batch processing capabilities for data streams. Proficiency in DataOps or MLOps methodologies and processes for integration and automation in cloud environments. – Lead a team of data scientists, machine learning engineers, to provide mentorship and foster innovation. Collaborate with stakeholders across departments to understand requirements and translate them into technical solutions. Promote knowledge sharing and best practices within the team and across the organization. – Stay current on emerging trends and technologies in video analytics, computer vision, and AI/ML. Experiment with state-of-the-art algorithms in machine vision, advanced Generative AI models, and time-series analysis models. Foster partnerships with academic institutions, research labs, or technology vendors to stay at the forefront of innovation. – Develop metrics and KPIs to evaluate the performance of video analytics systems. Implement continuous improvement strategies by iterating on models and algorithms. Ensure systems comply with ethical guidelines, data privacy laws, and fairness standards. – Present findings, insights, and recommendations to executives and other stakeholders. Quantify the Return on Investment (ROI) of analytics initiatives through case studies and success metrics. Drive adoption of AI/ML solutions across the organization by demonstrating tangible benefits. Minimum Qualifications: Education: An associate degree in computer science or a closely related field from an accredited college or university OR its equivalent in terms of total course credits/units Experience: Five (5) years of experience with probability and statistics, including experimental design, predictive modeling, optimization, and causal inference. Substitution: Additional experience as described above may be substituted for the required degree on a year-for-year basis (up to a maximum of two (2) years). One (1) year is equivalent to thirty (30) semester units/ forty-five (45) quarter units with a minimum of 10 semester / 15 quarter units in one of the fields above or a closely related field. Desirable Qualifications: – Bachelor’s or Master’s degree in applied mathematics, statistics, computer science, physics, engineering, or other relevant technical field. – Experience with machine learning concepts: regression and classification, clustering, feature selection, curse of dimensionality, bias-variance tradeoff, neural networks, SVMs, etc. – Knowledge in time-series analysis. – Familiarity with scripting language and/or shell scripting. – Software development life-cycle experience, with proven track record of shipping products. – Experience with big data and distributed system technologies like Hadoop, Mongo, Couch, Spark. – Knowledge of both SQL and NoSQL databases. – Knowledge AWS Sagemaker, Azure ML, GCP Vertex AI, or Snowflake Cortex. – Knowledge of Cloud Data Warehouses like Snowflake, Big query, Redshift, Databricks etc. – Experience in Java, Pig, Python, or Scala. – Knowledge or experience with security, machine learning, AWS Cloud (S3, EC2, ELB, EMR, CloudFormation) is a plus. – A highly collaborative mindset, eager to work cross-functionally with diverse teams and contribute to a shared mission.

Requirements