AI Infrastructure / ML Engineer
✨ AI Summary
We are seeking a skilled AI Infrastructure / ML Engineer to enhance our AI deployment capabilities. This role involves optimizing GPU usage and supporting the infrastructure for AI training and inference.
Main Responsibilities:
- Design and enhance AI deployment pipelines.
- Increase efficiency of GPU workloads for AI tasks.
- Provide support for AI training and inference frameworks.
- Optimize workloads using PyTorch, TensorFlow, and LLM technologies.
- Create scalable APIs and inference solutions.
- Develop tools for performance benchmarking and testing.
- Work closely with infrastructure teams on orchestration systems.
- Assist with model deployment and containerized AI workloads.
- Enhance the experience for AI developers.
- Monitor and fine-tune AI compute performance.
Success Criteria:
- Efficient and high-performing AI deployment infrastructure.
- Optimized GPU resource utilization.
- Reliable training and inference processes.
- Seamless onboarding for AI developers.
- Strong performance benchmarks and scalability.
Requirements:
- Master’s Degree in a relevant field.
- Experience in AI/ML infrastructure and MLOps.
- Proficient in Python programming.
- Experience with PyTorch, TensorFlow, or JAX.
- Familiarity with GPU computing and CUDA.
- Knowledge of containerized deployment.
- Proven experience in deploying AI models.
- Understanding of inference optimization.
- API and backend system development experience.
- Strong analytical and debugging capabilities.
Preferred Qualifications:
- Experience with LLM infrastructure.
- Familiarity with Hugging Face tools.
- Knowledge of distributed training systems.
- Experience with Kubernetes and orchestration.
- Contributions to open-source AI projects.
- Application Deadline: June 23, 2026
How to Apply:
Send your application to: collab@capa.cloud (Please include the job title in the subject line).
