Job Description
GENERAL DUTIES :
- NVIDIA Triton Inference Server Expertise : Leverage your in-depth knowledge of NVIDIA Triton to design and manage scalable and high-performance inference pipelines in a production, enterprise system.
- Model Deployment : Collaborate with data scientists and software engineers to deploy machine learning models, ensuring optimal performance, resource utilization, and cost tracking and savings.
- Scalability : Architect and implement solutions to scale machine learning inference to handle large workloads efficiently.
- Performance Optimization : Monitor and fine-tune model inference for optimal speed and resource utilization.
- Automation : Implement automation tools and processes for model deployment, monitoring, and scaling.
- Monitoring and Logging : Develop robust monitoring and logging solutions to track model performance, system health, and data quality in real-time.
- Security : Help implement security best practices to protect machine learning models and data.
- Documentation : Maintain detailed documentation of machine learning operations processes and best practices.
- Collaboration : Work closely with a cross-functional Product team to understand business requirements and translate them into technical solutions.
- Troubleshooting : Provide technical support for debugging and resolving issues related to model deployment and inference.
Required Skills
REQUIRED QUALIFICATIONS :
- Bachelor's or Master's degree in Computer Science, Software Engineering, or a related field.
- Proven experience (3+ years) as a Machine Learning Operations Engineer with a focus on NVIDIA Triton.
- Experience with other MLOps tools and platforms
- Strong programming skills in Python.
- Familiarity with machine learning frameworks like TensorFlow or PyTorch.
- Experience with GPU hardware and optimization for deep learning workloads.
- Strong problem-solving skills and the ability to work effectively in a collaborative team environment.
- Excellent communication skills and the ability to convey technical concepts to both technical and non-technical stakeholders.
- Solutions Architect Associate credential or other Associate (In Progress acceptable)
CLEARANCE :
Full Scope Polygraph minimum
Desired Skills
DESIRED QUALIFICATIONS :
- Proficiency in containerization technologies and orchestration tools (e.g., Docker, AWS Fargate, Amazon Elastic Container Service, AWS Elastic Kubernetes Service).
- Knowledge of DevOps practices and continuous integration / continuous deployment (CI / CD) pipelines
- Familiarity with the AWS cloud platform
- Previous experience in the deployment of machine learning models in production environments.
About Procession Systems
About us
30+ days ago