Machine Learning Engineer - Generalist, Automated Officiating

WORK OPTION: The NBA currently provides eligible employees the option of working remotely one day per week.

Group Summary:
The Basketball Strategy & Growth department is responsible for data collection, analysis and technology pertaining to all on-court activities. The group, in partnership with Referee Operations, oversees the Game Review Program to help drive improvements in referee performance and rules clarification initiatives. Basketball Strategy & Growth also leads pivotal initiatives focused on innovating and improving the NBA game, such as rules changes, improvements to the competition format and implementation of technologies to improve player health, game integrity and fan engagement. 

The Automated Officiating team is a new function within the Basketball Strategy & Growth department. This team is focused on innovating the on-court product through internally developed and deployed technologies. They spearhead key officiating technology initiatives from concept to launch, leveraging their cross-discipline expertise in real-time perception and sensing, computer vision, machine learning, and data analytics. The primary near-term focus of this team is deploying a system that can automatically detect and determine objective calls (e.g., out-of-bounds) in real-time during live NBA games.

Position Summary:
The NBA is seeking an experienced machine learning software engineer to be a key contributor to the Automated Officiating team. This team sits within Basketball Strategy & Growth, and its primary goal is to develop an advanced, multi-modal officiating product – leveraging computer vision and other sensing technologies – to enhance call accuracy, streamline game flow, and provide decision-making consistency and transparency. This is a small team that works like a startup within the NBA and provides significant opportunities for ownership and accelerated learning and growth.

Ideal candidates will bring considerable expertise building and owning ML pipelines in production and are enthusiastic to contribute to all aspects of a real-world perception system, from sensor processing pipelines to scalable ML data, training, modeling and evaluation pipelines.  This role will report to the Engineering Lead and play a critical role in taking our product from 0 to 1, leveraging expertise typically found in autonomous vehicles, robotics, AR/VR or other real-time ML-driven systems.

Major Responsibilities:

• Build and maintain scalable data pipelines that handle multi-modal sensor data, including video (high frame rates), sensor feeds, and player tracking data.
• Make technical contributions across the automated officiating system, e.g. sensor pipelines, ML data pipelines, training, model development and evaluation pipelines etc. 
• Develop efficient, scalable end-to-end pipelines to manage petabyte-scale datasets and model training throughout the entire ML lifecycle.
• Collaborate with data scientists, rules analysts, and the Engineering Lead to develop and integrate SOTA Perception solutions into the end-to-end officiating workflow.
• Define scalable system architectures that facilitate seamless integration of automated officiating into the NBA’s existing workflows.
• Collaborate with the broader Basketball R&D team on various initiatives, such as sensing research and development, KPI development and measurement, product road mapping, etc. 
• Collaborate with the Media Ops & Technology team to integrate system outputs with the Replay Center, broadcast partners, and virtual recreation providers.
• Provide technical guidance and mentorship to other engineers on the team. 
• Implement tooling and profiling for comprehensive analysis of the performance of the system. 
• Have a strong sense of ownership and be excited to wear many hats.
• Be a guardian of the codebase and push for clean, well-tested and highly extensible code.

Qualifications:

• Bachelor’s degree in Computer Science, Electrical Engineering, Math or related field (or equivalent experience). 
• Experience working with ML data pipelines and large datasets (TB or PB scale) in a production environment. 
• Demonstrated proficiency building and deploying machine learning solutions to production. 
• Proficiency in Python and prior experience building machine learning data pipelines.
• Familiarity with at least one deep learning framework (Pytorch, TensorFlow, JAX etc).
• Exposure to the entire ML stack, from data pipelines to model inference. 
• Excellent problem-solving skills and adaptability in a fast-paced environment. 
• Excellent communication and interpersonal skills.

Bonus Qualifications:

• Proven experience delivering solutions for real-world perception challenges (e.g., AR/VR, autonomous vehicles, robotics, drones). 
• Experience building systems to read, synchronize, and replay sensing input from a variety of sensors ranging from high-definition cameras to IMUs and audio sensors.
• Strong C++ programming skills (or another equivalent compiled on-board language), with a history of optimizing and deploying performance-critical systems. 
• Familiar with ML training frameworks (e.g., Pytorch Lightning) and prior experience building ML training and evaluation pipelines.
• Experience with production ML systems, including scalable data pipelines, training infrastructure, model evaluation and / or deployment.
• Familiarity with computer vision libraries, model deployment (TensorRT, ONNX) and GPU acceleration frameworks. 
• Strong grasp of low-latency, high-throughput system design, distributed task management systems and scalable model serving & deployment architectures.
• Exposure to CUDA, parallel computing, or high-performance programming on GPUs. 
• Background in sports analytics or experience working with sports-specific data.
• Passion for basketball and familiarity with officiating rules. 
   

Salary Range: $210,000 - $300,000

We Consider Applicants For All Positions On The Basis Of Merit, Qualifications And Business Needs, And Without Regard To Race, Color, National Origin, Religion, Sex, Gender Identity, Age, Disability, Alienage Or Citizenship Status, Ancestry, Marital Status, Creed, Genetic Predisposition Or Carrier Status, Sexual Orientation, Veteran Status, Familial Status, Status As A Victim Of Domestic Violence Or Any Other Status Or Characteristic Protected By Applicable Federal, State, Or Local Law.

The NBA is committed to providing a safe and healthy workplace.  To safeguard our employees and their families, our visitors, and the broader community from COVID-19, and in consideration of recommendations from health authorities and the NBA’s own advisors, any individual working onsite in our New York and New Jersey offices must be fully vaccinated against COVID-19. The NBA will discuss accommodations for individuals who cannot be vaccinated due to a medical reason or sincerely held religious belief, practice, or observance.