AISenior

AI Engineer (LLM, RAG, Agents)

Hanoi, Vietnam

Full-time

Remote-friendly

We're hiring an AI Engineer to design and ship production-grade LLM systems, RAG pipelines, and autonomous AI agents — not demos, not Jupyter notebooks. You'll work on real systems that process compliance documents for US fintechs, automate sales pipelines for B2B SaaS, and answer customer queries grounded in proprietary knowledge bases. We measure outputs in saved hours and ROI, not perplexity scores.

Apply by email Posted 2026-04-29 · Valid through 2026-07-28

Responsibilities

Design and build production LLM systems: integration, prompt engineering, fine-tuning, evaluation
Architect RAG pipelines: document ingestion, chunking, embedding, vector DB indexing, hybrid retrieval, re-ranking
Build autonomous AI agents with tool use, multi-agent orchestration, and human-in-the-loop checkpoints
Implement evaluation pipelines (RAGAS, custom evals) and continuously improve accuracy
Ship guardrails, observability (LangSmith / custom tracing), and cost optimization to production
Work directly with client tech leads on architecture decisions and trade-offs
Stay current on the LLM ecosystem (model releases, frameworks, eval methodologies)

Requirements

4+ years building production AI/ML systems (not just academic prototypes)
Strong Python (FastAPI, async, typing) and at least one of TypeScript / Go for service layer
Hands-on with OpenAI GPT-4o, Anthropic Claude 3.5, and at least one open-source model (Llama, Mistral)
Production RAG experience: chunking strategies, embedding selection, hybrid search, re-ranking
Vector DB experience: Pinecone, Weaviate, Qdrant, or pgvector — at least one in production
LangChain / LlamaIndex / LangGraph orchestration
AWS or GCP deployment, Docker, observability (Datadog / Grafana / LangSmith)
Business-level English (technical writing, code review, daily client standup)

Nice to have (priority hire)

Fine-tuning experience (LoRA, QLoRA, RLHF) on open-source models
Computer vision (YOLO, SAM, Detectron2) or multimodal LLM experience
Published technical content (blog, papers, conference talks)
Open-source contributions to AI/ML projects
JLPT N3+ Japanese or TOPIK 4+ Korean

Benefits

Competitive net salary + project bonus (top-of-market for senior AI engineers in Vietnam)
BHXH on full salary + premium health insurance
100% senior AI team — work alongside engineers from prior roles at AI-native startups
Direct ownership of architecture decisions, no PM filtering
Generous annual learning budget (papers, courses, conferences — NeurIPS / ICML if you present)
GPU credits for experimentation (AWS / Modal / RunPod)
Macbook M3 Pro / M4 + dual monitor, premium dev tools (Cursor Pro, Copilot Pro)
Conference travel budget (international AI conferences encouraged)
Stock option discussion after 12 months

How to apply

1. Send your CV (+ GitHub / portfolio link) to [email protected]
2. Subject line: [AI Engineer] [Full Name] — [Years of exp] — [GitHub / portfolio]
3. Optional but bonus: a short note (≤ 200 words) about a recent project you're proud of — what you built, hardest decision, what you learned.
4. Rolling reviews — we hire when we find the right person.

Email your application See other openings

AI Engineer (LLM, RAG, Agents)

Hanoi, Vietnam

Full-time

Remote-friendly

Apply by email Posted 2026-04-29 · Valid through 2026-07-28

Responsibilities

Design and build production LLM systems: integration, prompt engineering, fine-tuning, evaluation

Architect RAG pipelines: document ingestion, chunking, embedding, vector DB indexing, hybrid retrieval, re-ranking

Build autonomous AI agents with tool use, multi-agent orchestration, and human-in-the-loop checkpoints

Implement evaluation pipelines (RAGAS, custom evals) and continuously improve accuracy

Ship guardrails, observability (LangSmith / custom tracing), and cost optimization to production

Work directly with client tech leads on architecture decisions and trade-offs

Stay current on the LLM ecosystem (model releases, frameworks, eval methodologies)

Requirements

4+ years building production AI/ML systems (not just academic prototypes)

Strong Python (FastAPI, async, typing) and at least one of TypeScript / Go for service layer

Hands-on with OpenAI GPT-4o, Anthropic Claude 3.5, and at least one open-source model (Llama, Mistral)

Production RAG experience: chunking strategies, embedding selection, hybrid search, re-ranking

Vector DB experience: Pinecone, Weaviate, Qdrant, or pgvector — at least one in production

LangChain / LlamaIndex / LangGraph orchestration

AWS or GCP deployment, Docker, observability (Datadog / Grafana / LangSmith)

Business-level English (technical writing, code review, daily client standup)

Benefits

Competitive net salary + project bonus (top-of-market for senior AI engineers in Vietnam)

BHXH on full salary + premium health insurance

100% senior AI team — work alongside engineers from prior roles at AI-native startups

Direct ownership of architecture decisions, no PM filtering

Generous annual learning budget (papers, courses, conferences — NeurIPS / ICML if you present)

GPU credits for experimentation (AWS / Modal / RunPod)

Macbook M3 Pro / M4 + dual monitor, premium dev tools (Cursor Pro, Copilot Pro)

Conference travel budget (international AI conferences encouraged)

Stock option discussion after 12 months

How to apply

1. Send your CV (+ GitHub / portfolio link) to [email protected]

2. Subject line: [AI Engineer] [Full Name] — [Years of exp] — [GitHub / portfolio]

3. Optional but bonus: a short note (≤ 200 words) about a recent project you're proud of — what you built, hardest decision, what you learned.

4. Rolling reviews — we hire when we find the right person.