Artificial Intelligence Engineer
HomeTeam Network is seeking an AI Engineer to develop solutions for their AI-complete sports broadcasting platform. The role involves working on computer vision and machine learning systems to enhance sports video processing and real-time content generation.
Responsibilities
- Implement and optimize computer vision models for real-time player tracking, action recognition, and game state detection in sports video
- Build ML inference pipelines using ONNX Runtime and TensorRT for GPU-accelerated model deployment
- Develop multiprocess video processing pipelines for high-throughput RTMP/RTSP/SRT streams
- Integrate AI systems with AWS infrastructure (ECS, Lambda, Step Functions, EventBridge) and cloud deployment workflows
- Optimize real-time video processing performance using FFmpeg, OpenCV, and CUDA
- Deploy and monitor AI models in cloud‑native production using cloud platforms and Weights & Biases for end‑to‑end observability
- Create testing frameworks to validate model accuracy and pipeline reliability
- Collaborate with DevOps on infrastructure-as-code using Terraform for AWS and GCP deployments
- Research and implement emerging AI technologies to improve our platform
Skills
- 1-3 years of software development experience (AI/ML focus preferred)
- Strong Python programming skills with experience in:
- Deep learning inference frameworks (ONNX Runtime, TensorRT)
- Computer vision libraries (OpenCV, torchvision)
- Data processing and numerical computing (NumPy, Pandas)
- Multiprocessing and concurrent programming
- Understanding of ML fundamentals and neural network architectures
- Experience with Git and collaborative development practices
- Bachelor's degree in Computer Science, Engineering, or related field (or equivalent experience)
- Ability to troubleshoot complex technical issues in production systems
- Excellent communication and teamwork skills
- Experience with video streaming protocols (RTMP, RTSP, SRT) and FFmpeg
- Knowledge of real-time system optimization and low-latency processing
- Experience with cloud infrastructure (AWS ECS, Lambda, Step Functions, or GCP equivalents)
- Understanding of MLOps practices and model deployment pipelines
- Familiarity with infrastructure-as-code tools (Terraform)
- Experience with experiment tracking tools (Weights & Biases, MLflow)
- Published research in computer vision or machine learning
Company Overview