Location: Seattle, Washington, 98103, United States of America
Job Summary:
Job Duties
- Contribute to backend services for Firefly powering Generative AI features.
- Develop GPU optimized model pipelines for custom AI solutions.
- Ensure scalable, reliable cloud services with observability and logging.
- Contribute to Project Colligo for managing ML model inference and training.
- Develop business logic for Firefly services, including usage metering and entitlement checks.
Required Skills (Keywords)
- GPU intensive ML workloads
- Cloud services architecture
- Model serving
- Orchestration
- Software engineering
- Python, ML, PyTorch, CUDA, AWS, Kubernetes
Required Experiences (Topics)
- Experience in production environments
- Scaling for large-scale use (5B+ requests/month)
- Extensive software engineering background
Job URLs: