Machine Learning Infrastructure Engineer, 3D Model Inference & Deployment

Job Description

Genies, an AI avatar and games technology company, is seeking an ML Infrastructure Engineer to contribute to the development of highly configurable digital avatars and content creation tools. The role involves designing and implementing machine learning models, conducting data analysis, and developing sophisticated algorithms for optimization and deployment challenges. The candidate will collaborate with cross-functional teams to deploy machine learning systems and stay updated with advancements in machine learning and artificial intelligence.

Responsibilities:

• Deploy generative 3D models (Diffusion, GANs, VAEs, NeRF, Gaussian Splatting) in cloud environments.
• Optimize inference pipelines (ONNX, TensorRT, Triton, CUDA, PyTorch) for 3D model serving.
• Develop scalable cloud architectures (AWS, Kubernetes, Lambda, GitHub Actions) for real-time 3D asset generation.
• Work with graphics teams to integrate ML models into rendering pipelines.
• Implement distributed training and fine-tuning workflows for 3D models.

Requirements:

• Bachelor's degree in Computer Science, Data Science, Statistics, or a related field.
• 5+ years of experience in machine learning or related fields.
• Experience with data structures, data modeling, and software architecture.
• ML deployment & optimization (TensorRT, ONNX, Triton, CUDA, PyTorch).
• Cloud orchestration & CI/CD (AWS, Kubernetes, GitHub Actions, Terraform).
• Scalability experience with large 3D datasets & generative models.
• Knowledge of 3D data formats (USD, glTF, FBX) and processing.
• C++ experience for high-performance ML execution.

Genies offers:

• Comprehensive health insurance.
• Competitive salaries.
• Unlimited paid time off.
• Health & wellness support programs.
• Flexible hours and hybrid work policy