CÔNG TY TNHH ZEN8 VIỆT NAM ★ 5.0

Position:                   AI ENGINEER (Mid-level)

Department:           Solutions Team

Status:                      Fulltime        

Update:                    2026

Work location:       TT03A-13, Mo Lao New Urban, Ha Dong, Hanoi City

Our Company

zen8labs is a global technology consultancy founded in 2019 by our talented founders - coming from prestigious backgrounds such as Google, Facebook, and Planday... We specialize in three main areas - customer experience design, enterprise modernization, and digital transformation. Despite the short period of time, zen8labs’ portfolio of previous successes includes big names, from Vietnamese corporates such as Vingroup to worldwide businesses such as Invitae (US), ClinikNote (Australia), and WebProof (Denmark)... Joining zen8labs not only allows a solid exposure to technology management but also grants the opportunity to learn from some of the best people that the industry can offer and expand one’s delivery capability.

Learn more about zen8labs at: https://www.zen8labs.com/                 

Reporting

The AI Engineer reports directly to Project Manager and Head of Solutions.

Role Overview

We are looking for a Mid-Level AI Engineer to design and build AI-powered applications and agent systems for our enterprise clients. You will own AI features from ideation through prototyping to production — integrating LLMs, building RAG pipelines, and developing multi-agent workflows that deliver real business value.

Duties and Responsibilities

The AI Engineer is responsible for tasks in the following areas: 

• Design and build AI-powered features using both closed-source LLM APIs (OpenAI, Anthropic Claude …) and open-source models (LLaMA, Qwen …) — chatbots, copilots, semantic search, content automation, and workflow automation
• Develop RAG pipelines connecting models to internal data sources using embeddings and vector databases
• Design and implement AI agent workflows — tool-calling, multi-step planning, memory management, and human-in-the-loop controls using frameworks such as LangChain, LangGraph or AutoGen
• Apply context engineering strategies — system prompts, few-shot examples, memory, and RAG context assembly — to achieve reliable, production-grade LLM behavior
• Monitor AI features for performance, quality, latency, and cost; add logging, tracing, and guardrails to maintain reliability
• Rapidly prototype solutions to validate ideas and contribute to pre-sales technical proposals
• Build reusable AI modules and services that can be shared across multiple client projects
• Stay current with emerging LLM tools and agent frameworks; propose improvements to the team's stack and practices

Qualifications/ Experience Requirements:

Must Have:

• Bachelor's degree or higher in Computer Science, Software Engineering, or a related field
• Strong systems thinking and a solid foundation in computer science fundamentals and mathematics.
• 2+ years of software engineering experience with strong Python skills and clean, maintainable coding practices
• Hands-on experience integrating LLM/AI APIs (OpenAI, Anthropic, or similar) in at least one real project
• Solid understanding of web backends — REST APIs, authentication, error handling, and basic security
• Familiarity with context engineering (system prompts, few-shot examples, guardrails) and basic understanding of RAG concepts (embeddings, vector stores, context retrieval), and at least one agent framework
• Foundational understanding of traditional ML concepts (classification, regression, clustering) and common frameworks such as scikit-learn or XGBoost — useful for hybrid solutions that combine LLMs with structured data models
• Experience deploying or serving models locally or on cloud infrastructure (Ollama, vLLM, Hugging Face Inference, or similar)
• Ability to take ownership of tasks and deliver from prototype to production with minimal supervision
• Good communication skills; comfortable working with both technical and non-technical stakeholders

Nice to have:

• Experience with vector databases (Pinecone, Weaviate, Qdrant, pgvector) and RAG frameworks (LangChain, LlamaIndex)
• Hands-on experience building AI agent systems: tool-calling, multi-step workflows, and multi-agent coordination
• Experience with AI/agent evaluation: prompt testing, scenario-based evaluation, or A/B testing of workflows
• Familiarity with cloud platforms (AWS, GCP, or Azure) and containerized deployments using Docker
• Knowledge of fine-tuning or parameter-efficient training (LoRA/QLoRA) to adapt pre-trained models for domain-specific tasks
• Familiarity with MCP (Model Context Protocol) or no-code agent builders such as n8n or Flowise

What we offer

• Salary and bonus

-      Attractive salary;

-      100% salary on probation;

-      Performance review twice a year, based on job outcomes;

-      13 months salary and bonus assessment yearly;

-      Working time: Flexible working hours and location from Mondays to Fridays.

-      Unlimited paid leave annually;

• Insurance, health care, and extra benefits

-      Premium PTI health care insurance;

-      Special health benefits (50% discount on medical examination fee​, 10% discount on ultrasound and procedure fees​, 5% on medicine) at 2 Clinics, including:

Vivision - 514 Bạch Mai

Phụ Sản 1 - 329 Bạch Mai

-      An annual medical check-up;

-      Annual company trip and holiday party and other benefits according to company policy;

-      Free lunch at the office; drinks and snacks at the pantry;

-      MacBook and external monitor provided for work;

• Working environment and development

-      Working environment: fast-moving, young, dynamic, no-walls environment.

-      Sports activities: football, exercise break.

-      Training: soft skills and technical skills training.

-      Others: free coffee/tea/cookies, parking fee, year-end party, etc…

Join our team to become part of an amazing group of tech talents!

If you are interested in this vacancy, please send your application or contact us directly via:

Email: [email protected]

Mobile/Zalo: 0962019986 (Ms. Hien)