To apply for this job, you need to complete both steps below:

STEP 1:

Please send your CV to this email to submit your application directly to the company: 

careerservice@vinuni.edu.vn

Your application will only be received by Recruiter if submitted via above email.

STEP 2:

Kindly scroll to the bottom of this page and complete the short VinUni Tracking Form.

Filling out this form alone does not count as applying. Kindly remind this form is not part of the company’s application process. It only helps Careers, Alumni, Industry and Development (CAID) Department discover more opportunities and follow up in case of system issues.

You will have the opportunity to participate in on-site interviews for the following position at VinUni Tech Career Day 2026:

We are seeking a motivated AI / LLM Engineer Intern to learn by contributing to real Generative AI

projects. Under guidance from experienced engineers, you will apply modern AI engineering

practices in real project contexts. The areas below are learning goals and project exposure during the

internship; production-level mastery is not expected at entry.

 

RAG, LLM & Agentic AI Development

• Learn and apply RAG fundamentals using LangChain, including document ingestion,

chunking, embeddings, VectorStores, retrievers, tool calling, and prompt engineering in real

project scenarios.

• Gain hands-on experience designing and implementing simple agent workflows with

LangGraph, including state machines, routers, supervisors, tool execution, multi-agent

orchestration, retries, and human-in-the-loop patterns under guidance.

• Support experiments and evaluation of retrieval and LLM quality, including relevance, answer

quality, hallucination reduction, latency, and cost, while learning how these trade-offs are

handled in practice.

Backend, Data & Retrieval Engineering

• Learn to develop Python backend components and REST APIs for model inference, retrieval

pipelines, tool integration, and workflow automation, with FastAPI as the preferred

framework.

• Gain practical experience with embeddings, vector databases such as FAISS or Chroma,

caching, indexing, filtering, context construction, data preprocessing, and retrieval

optimization.

• Support testing, debugging, logging, and performance improvement activities while learning

production-oriented backend and data engineering practices.

Cloud, Containerization & Engineering Practices

• Gain introductory hands-on exposure to deploying and operating AI services on AWS, GCP, or

Azure, including common capabilities such as model/API hosting, object storage,

configuration, logging, and monitoring, when relevant to project tasks.

• Learn to containerize and run AI services with Docker, with opportunities to gain exposure to

Kubernetes, CI integration, basic cloud security, and cost-awareness practices under

guidance.

Practice professional engineering workflows using Git/GitHub, including branching, pull requests,

code review, documentation, collaboration, feature implementation, and bug fixing with the team.

REQUIRED QUALIFICATIONS

Candidate Profile

• Final-year student, recent graduate, or early-career candidate in Computer Science,

Software Engineering, Artificial Intelligence, Data Science, or a related field, with strong

willingness to learn and relevant hands-on work through coursework, research, personal

projects, internships, or open-source contributions.

Required Skills

• Solid Python programming fundamentals and a basic understanding of REST APIs and

backend development.

• Basic understanding or hands-on exposure to RAG concepts and LangChain through

coursework, personal projects, research, or previous internships.

• Basic understanding or hands-on exposure to agentic AI concepts; familiarity with

LangGraph, state machines, routers, supervisors, or multi-agent workflows is an advantage.

• Understanding of core LLM application concepts such as model inference, retrieval

pipelines, prompt engineering, and workflow automation.

• Understanding of embeddings, vector search/vector databases (e.g., FAISS, Chroma),

caching concepts, and retrieval fundamentals.

• Basic Docker usage or willingness to learn containerized development; Kubernetes exposure

is a plus.

• Comfortable with Git/GitHub fundamentals, including branches, commits, and pull requests;

basic CI awareness is a plus

Nice to Have

• Basic familiarity or hands-on exposure to at least one cloud environment (AWS/GCP/Azure),

including model/API hosting, API gateways, object storage (S3/GCS/Blob Storage), logging,

and monitoring.

• Experience with advanced RAG patterns such as query planning, tool routing, multi-step

reasoning, re-ranking, and hallucination reduction.

• Familiarity with AI observability tools such as LangSmith, Phoenix, or OpenTelemetry for LLM

applications.

• Exposure to MLOps toolchains such as MLflow, Kubeflow Pipelines, model registries,

evaluation, and deployment workflows.

• Experience with backend frameworks such as FastAPI or NodeJS/NestJS for serving AI

features.

• Knowledge of front-end integration for AI products, such as React, chat interfaces, or

streaming UI.

• Familiarity with Backstage or internal developer platforms for AI/ML workflows.

Soft Skills

• Strong problem-solving mindset and willingness to learn quickly.

• Ability to communicate progress, blockers, and technical trade-offs clearly.

• Ability to work collaboratively, receive feedback, and follow engineering guidance.

• Good reading and communication skills in English are an advantage.

BENEFITS

• Internship allowance and benefits according to company policy.

• Hands-on experience with modern Generative AI, RAG, agentic AI, cloud, and software

engineering stacks.

• Mentoring and technical guidance from experienced AI engineers.

• Opportunity to contribute to real AI/ML projects for global clients.

• Learning, training, and potential career-development opportunities within FPT Software.