Innotech Vietnam

Overview of job

As an AI Engineer Level 3, you will lead LLM development, AI infrastructure scaling, and distributed training. You will optimize high-performance AI systems, manage multi-GPU environments, and deploy AI models at scale. Build and lead a team, enhancing overall technical capabilities and performance. 

Key Responsibilities: 

• Make a proposal of AI solution in align with a set of customer requirements and goal. 
• Build and lead a team, enhancing overall technical capabilities and performance. 
• Optimize Large Language Models (LLMs) & AI models, including: 
• Efficient training of LLMs (DeepSpeed, FSDP, LoRA) 
• Deploying models with Kubernetes, Ray, Triton Inference Server 
• Optimizing model inference speed with ONNX, TensorRT, GGUF, vLLM 
• Implementing Retrieval-Augmented Generation (RAG) pipelines 
• Applying AI distillation and quantization techniques 
• Work with HPC infrastructure and distributed AI computing. 
• Implement system monitoring tools (htop, tcpdump, iostat, netstat). 
• Troubleshoot AI system performance bottlenecks. 

• 13th-month salary calculated based on actual working time at INNOTECH.
• PVI Healthcare Insurance for all employees
• PVI Healthcare Insurance for family
• Moon cake, Tet Gift
• Quarterly/project kickoff team-building budget.
• Resolution laptop and monitor provided for work.
• Performance bonus plan.
• Employee referral bonus: 2,000,000 – 10,000,000 VND (depending on level/role).
• Working hours: Monday to Friday.
• Annual company trips / Football club / Climbing club / Year-end party.
• Learning and certification support.
• Value-oriented, international working environment with a flexible culture.

• Bachelor’s or Master’s degree in AI, Computer Science, Machine Learning or a related field. 
• 3+ years of experience in LLM model development and optimization. 
• Hands-on experience with distributed AI training and HPC for AI workloads. 
• Expertise in GPU acceleration (CUDA, TensorRT, vLLM). 
• Deep understanding of LLM architectures (GPT, Llama, Falcon, T5, Mistral). 
• Experience in cloud AI deployment (Kubernetes, OpenStack, Ray, Triton). 
• Strong ability to troubleshoot system errors and optimize AI workloads. 
• English communication, reading, writing professional