Agentic AI Engineer (LLM)

VINFAST is a pioneering electric vehicle (EV) company committed to revolutionizing the automotive  industry with sustainable and innovative mobility solutions. As a leading player in the EV market,  VinFast is dedicated to delivering high-quality, cutting-edge electric vehicles that redefine the driving  experience. Our team consists of passionate professionals driven by a shared vision of creating a greener and  more sustainable future through innovation, technology, and excellence. 

In this role, you will be instrumental in SLP Center, using your skills to process and analyze  large volumes of data. You will collaborate with diverse teams, including Engineering, Quality Control,  VINFAST's suppliers, to create cutting-edge solutions that will drive the future of transportation. 

• Design, develop, and optimize LLM-based AI Agents for real-world applications with a focus on accuracy, latency, scalability, and reliability.  
  

• Research, evaluate, and integrate state-of-the-art foundation models (OpenAI, Gemini, Claude, open-source LLMs, etc.) for different AI tasks.  
  

• Fine-tune, align, and optimize large language models using techniques such as SFT, LoRA/QLoRA, DPO, preference optimization, and model distillation.  
  

• Design multi-agent systems, agent orchestration, planning, memory, tool calling, and workflow execution architectures.  
  

• Develop Retrieval-Augmented Generation (RAG) pipelines, including retrieval, reranking, indexing, embedding optimization, and knowledge integration.  
  

• Design and optimize function calling pipelines for structured task execution and external tool integration.  
  

• Build evaluation frameworks for AI systems, including automated benchmarking, offline evaluation, online A/B testing, and hallucination detection.  
  

• Optimize model inference performance through prompt engineering, routing, caching, batching, quantization, speculative decoding, and serving optimization.  
  

• Develop and maintain APIs and reusable AI services for rapid integration into products.  
  

• Build observability capabilities including logging, tracing, monitoring, and performance analytics for AI agents in production.  
  

• Continuously research emerging AI technologies, models, and agent frameworks, rapidly validating and applying promising approaches to production systems.  
  

• Collaborate with product managers, backend engineers, frontend engineers, and infrastructure teams to deliver production-ready AI features.  
  

• Produce technical documentation, architecture designs, best practices, and reusable components for the AI platform.  
  

• Mentor junior engineers, conduct technical reviews, and contribute to engineering standards and AI best practices
  

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Software Engineering, or a related field.  
  

• 3+ years of experience in AI/ML engineering, NLP, LLM applications, or a related software engineering role. (Adjust based on seniority.)  
  

• Strong understanding of Large Language Models (LLMs), Transformer architectures, and modern generative AI techniques.  
  

• Hands-on experience building AI agents using frameworks such as LangGraph, LangChain, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or equivalent.  
  

• Experience designing and implementing Retrieval-Augmented Generation (RAG) systems, including embedding models, vector databases, retrieval, reranking, and knowledge indexing.  
  

• Experience fine-tuning LLMs using techniques such as LoRA, QLoRA, Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), or other parameter-efficient training methods.  
  

• Strong programming skills in Python and familiarity with AI/ML libraries such as PyTorch, Hugging Face Transformers, PEFT, vLLM, or equivalent.  
  

• Experience integrating foundation models through APIs (OpenAI, Gemini, Anthropic, or open-source LLMs) and evaluating model performance.  
  

• Solid understanding of prompt engineering, function calling, structured output generation, tool integration, and agent orchestration.  
  

• Experience deploying AI services in production environments, including model serving, inference optimization, containerization (Docker), and cloud platforms.  
  

• Knowledge of observability for AI systems, including logging, tracing, monitoring, evaluation pipelines, and performance analysis.  
  

• Familiarity with software engineering best practices, including Git, CI/CD, API development, testing, and code review.  
  

• Strong analytical and problem-solving skills with the ability to rapidly evaluate and adopt emerging AI technologies.  
  
• Excellent communication skills and ability to collaborate effectively in cross-functional teams.  
  Preferred Qualifications 
  
• Experience with distributed model training and inference optimization (DeepSpeed, FSDP, TensorRT-LLM, vLLM, SGLang, etc.).  
  
• Experience with multi-agent systems, workflow orchestration, planning, and memory architectures.  
  
• Knowledge of model evaluation methodologies, benchmarking, hallucination detection, and AI safety.  
  

• Experience building voice agents, conversational AI, or virtual assistants.  
  

• Contributions to open-source AI projects, research publications, Kaggle competitions, or personal AI projects are a plus.  
  

• Familiarity with Kubernetes, GPU infrastructure, distributed systems, and MLOps platforms is preferred.