AI Engineer (Machine Learning/LLM/API) Up to 5x M VND

Mô tả công việc

About the position

CLUEGA Company is looking for a AI Engineer with strong experience in Machine Learning, Deep Learning, NLP, LLM, RAG and AI Agent development, who can directly participate in researching, designing, building and deploying AI solutions into real products.

The right candidate is someone who has a solid technical foundation in AI/ML, understands how to work with real-world data, and is capable of moving from research, experiment, prototype to production deployment.

The candidate should be able to work with large-scale data from APIs, databases and internal systems, design suitable AI pipelines, and apply LLM-based solutions such as RAG, semantic search, AI Agent, function calling, tool calling, text classification, summarization, prediction and recommendation.

Product / Project Description

Applicants will be involved in developing AI capabilities for the company’s internal systems, including:

• AI system for reading, analyzing and understanding data from TikTok API and internal databases.
• AI assistant / chatbot for querying advertising data, content data and business performance.
• AI Agent system capable of planning, calling tools, using APIs and supporting business workflows.
• RAG system for retrieving internal documents, historical data, API data and product knowledge.
• Semantic search system using vector database and embedding models.
• NLP modules for multilingual text processing, especially Vietnamese, English and Chinese.
• Prediction and recommendation modules for advertising performance, content performance and operational insights.
• Backend / API modules related to AI inference, data processing, model serving and integration with internal systems.
• Future expanding products / platforms related to social media, entertainment, advertising and digital content operations.

The project’s current / expected tech stack includes:

Python, PyTorch, Transformers, LangChain / LlamaIndex, FastAPI, Vector Database, PostgreSQL, ClickHouse, Redis, Docker, Next.js, NestJS, Golang, TikTok API, Facebook API.

Job Responsibilities

1. AI / Machine Learning Development

• Research, design and develop AI/ML solutions for internal products and business use cases.
• Build machine learning models for classification, prediction, recommendation, ranking or anomaly detection when needed.
• Work with structured and unstructured data from databases, APIs, logs, documents and user interactions.
• Analyze business requirements and convert them into suitable AI tasks, model objectives and evaluation metrics.
• Build end-to-end AI pipelines from data collection, preprocessing, feature engineering, training, evaluation to deployment.
• Experiment with different model architectures and approaches to improve model quality and system performance.
• Evaluate model results using suitable metrics and real business scenarios.
• Collaborate with backend, frontend, product and business teams to integrate AI features into production systems.

2. NLP / LLM Development

• Develop NLP pipelines for text classification, intent detection, entity extraction, summarization, generation and multilingual processing.
• Work with Large Language Models for prompt engineering, fine-tuning, RAG, function calling and tool calling.
• Design prompts, system instructions and evaluation flows for LLM-based applications.
• Build AI chatbot / AI assistant features that can understand user questions and return accurate, useful and context-aware answers.
• Handle multilingual NLP problems involving Vietnamese, English and Chinese content.
• Improve LLM response quality by using retrieval, memory, structured outputs, validation and post-processing.
• Design guardrails and fallback strategies to reduce hallucination, incorrect answers and unsafe outputs.
• Build evaluation datasets and test cases for LLM quality assessment.

3. RAG / Semantic Search / Vector Database

• Design and build Retrieval-Augmented Generation systems for internal documents, API data and database-driven knowledge.
• Build data ingestion pipelines for documents, APIs, database records and business data.
• Design chunking strategy, embedding strategy, indexing strategy and retrieval strategy.
• Work with vector databases such as Qdrant, Milvus, Weaviate, Pinecone, FAISS or equivalent tools.
• Optimize retrieval quality using hybrid search, reranking, metadata filtering and query rewriting.
• Evaluate RAG system quality based on answer accuracy, retrieval relevance, latency and user feedback.
• Design caching, context compression and ranking mechanisms to handle large-scale data without exceeding LLM context limits.
• Work with continuously updated data from APIs and databases to keep AI knowledge fresh and reliable.

4. AI Agent / Tool Calling / Automation

• Develop AI Agent systems capable of planning, reasoning, calling tools and interacting with internal APIs.
• Design tool schemas, function calling flows and API integration patterns for AI Agents.
• Build agents that can support data analysis, advertising performance review, report generation and operational workflows.
• Integrate AI Agents with internal services, databases, third-party APIs and MCP-like tool systems when needed.
• Handle agent memory, execution state, error handling and permission boundaries.
• Monitor and improve agent reliability, response quality and tool execution accuracy.
• Design clear logs, traces and debugging mechanisms for AI Agent behavior.

5. Model Training / Fine-tuning / Optimization

• Train or fine-tune models for specific business problems when necessary.
• Work with embedding models, classification models, reranking models and transformer-based models.
• Prepare datasets, clean data, label data and build evaluation sets.
• Apply fine-tuning techniques such as LoRA, QLoRA, instruction tuning or supervised fine-tuning when suitable.
• Optimize model inference using quantization, batching, caching and distributed inference.
• Work with GPU environments for training and inference optimization.
• Evaluate trade-offs between using closed-source LLM APIs, open-source models and self-hosted models.
• Support model serving, monitoring and version management in production.

6. Process, Reporting and AI Quality Improvement

• Communicate, update progress and discuss technical issues through Lark or internal company channels.
• Write clear technical documentation for AI architecture, model behavior, data flow and API integration.
• Proactively suggest improvements to AI pipeline, model quality, data quality and system performance.
• Collaborate with QA team to design test cases for AI outputs, RAG results and agent behavior.
• Support the development of internal AI engineering standards for the team.
• Use AI tools such as ChatGPT, Claude, Gemini or equivalent tools to support research, coding, debugging, documentation and evaluation.

Yêu cầu công việc

Required Requirements

• Have at least 4–5 years of experience in AI Engineer, Machine Learning Engineer, NLP Engineer, Data Scientist or equivalent position.
• Strong background in Machine Learning, Deep Learning and NLP.
• Experience working with transformer-based models and modern LLM applications.
• Experience building LLM-based systems such as chatbot, AI assistant, RAG or AI Agent.
• Strong Python programming skills.
• Experience with PyTorch, Hugging Face Transformers or equivalent ML/DL frameworks.
• Experience designing and building data pipelines for model training or AI inference.
• Experience working with APIs, databases and backend services.
• Understand the basic and advanced concepts of:
  • Machine Learning.
  • Deep Learning.
  • NLP.
  • Embedding models.
  • Vector database.
  • Retrieval-Augmented Generation.
  • Fine-tuning.
• Experience with at least one of the following:
  • LangChain.
  • LlamaIndex.
  • Anthropic Claude API.
  • Hugging Face.
  • Qdrant / Milvus / Weaviate / FAISS.
• Ability to read and understand technical documents, research papers and API documents in English.
• Logical, proactive, research-oriented and able to solve open-ended technical problems.
• Ability to work independently, self-organize and adapt quickly in a startup environment.
• Have a high sense of responsibility, not only build AI features but also care about accuracy, reliability, maintainability and production impact.

Priority Request

• Experience building AI systems for real production products.
• Experience with RAG systems over large-scale data, frequently updated data or multi-source data.
• Experience with AI Agent, tool calling, function calling or MCP-related architecture.
• Experience with social media, advertising, user data, content data or administration dashboards is an advantage.
• Experience working with third-party APIs such as TikTok API, Facebook API, Google API or equivalent platforms.
• Experience with multilingual NLP, especially Vietnamese, English.
• Experience fine-tuning open-source LLMs or embedding models.
• Experience optimizing inference cost, latency and throughput.
• Experience with model serving tools such as vLLM, TGI, Triton, Ray Serve or FastAPI.
• Experience with data systems such as PostgreSQL, ClickHouse, Redis, Kafka or message queues.
• Basic knowledge of Next.js, NestJS, Golang, Docker and microservices is advantageous.
• Experience using AI tools like ChatGPT / Claude / Gemini / Cursor / Copilot to improve development productivity.
• Knowing Chinese is an advantage, not a requirement.

Soft Skills

• Communicate clearly and proactively ask when the requirement is unclear.
• Good coordination with Developer, Product / Business, QA and related departments.
• Strong problem-solving mindset and ability to break down complex AI problems.
• Careful, responsible and ownership-oriented with AI output quality.
• Ability to work in fast-changing environments that require flexible technical decisions.
• Good product thinking, care about user experience and system reliability.
• Willing to research new tools, frameworks, models and AI architectures when the project needs them.
• Able to explain technical AI concepts clearly to non-AI team members.

Applicant Evaluation Process

Applicants may be required to perform a short technical discussion or live test during the interview process to assess their ability to analyze AI problems, design AI architecture, reason about data and choose suitable technical approaches.

Live test content may include:

• Analyze a real business scenario and propose an AI solution.
• Design a RAG pipeline for internal documents, API data or database records.
• Design an AI Agent flow that can call internal APIs or tools.
• Explain how to evaluate the quality of an LLM / RAG / AI Agent system.
• Discuss how to handle hallucination, outdated data, wrong retrieval or large context problems.
• Review a simple AI pipeline and identify potential issues.
• Write or explain pseudo-code for data processing, embedding, retrieval or model inference.
• Discuss whether a problem should use rule-based logic, classical ML, fine-tuning, RAG or AI Agent.

Prefer candidates who can think practically, balance research and production, and explain 

Tại sao bạn sẽ yêu thích làm việc tại đây

• Salary: 2x.xxx.xxx – 5x.xxx.xxx VNĐ/month, depending on ability.
• Participate in social insurance, health insurance fully as prescribed.
• Working in a startup environment, the product develops quickly and has many opportunities to participate in AI system design from an early stage.
• Opportunity to build real AI products related to social media, advertising data, content data and platforms such as TikTok, Facebook, Zalo in the future.
• Opportunity to work from research to production, including RAG, AI Agent, LLM integration, model optimization and data-driven AI systems.