Hiring MLOPS ENGINEER (AI Infrastructure)
Hiring MLOps Engineer at Trivita AI to manage AI infrastructure, deploy LLMs, optimize GPU usage, and build scalable MLOps pipelines.
Job description
- Deploy and manage LLM serving systems (vLLM, TGI, Triton) and optimize inference performance using techniques such as PagedAttention and quantization
- Build and manage GPU infrastructure, including NVIDIA MIG configuration for efficient resource utilization
- Design and develop CI/CD pipelines for machine learning, including automated testing, deployment, and model versioning
- Implement monitoring systems for GPU health, latency, throughput, and model drift
- Design auto-scaling mechanisms for AI workloads on Kubernetes
- Collaborate with Backend Developers and AI Researchers to integrate models into production systems
Technical requirements
- Strong expertise in Docker and Kubernetes, including GPU operator and resource scheduling
- Deep understanding of NVIDIA GPU architecture and MIG
- Proficiency in Python and shell scripting
- Experience with ML frameworks such as PyTorch or TensorFlow
- Experience with MLOps tools (Kubeflow, MLflow, Weights & Biases)
- Experience with cloud platforms (AWS, GCP)
- Familiarity with backend languages (Java or Go) is a plus
Qualifications
- At least 3 years of experience in MLOps, DevOps, or SRE
- Proven experience managing production-grade AI/ML systems
- Bachelor’s degree in Computer Science, Information Technology, or related field
Benefits
- Work with experienced AI engineers and experts
- Mac provided for work
- Full social insurance based on gross salary
- Modern working environment
- Access to facilities such as swimming pool, gym, and table tennis
Contact information
- Address: No. 01, Street 104, Quarter 3, Binh Trung Ward, Ho Chi Minh City
- Phone: 0909797699
- Email: hr@trivita.ai
