Senior AI Engineer — LLMs, RAG & Production AI

ThoughtFull; Kuala Lumpur; On-site; MYR 93,000 - 148,000; Full time

Job summary

ThoughtFull is seeking an experienced AI/ML Engineer to design, build, and deploy scalable AI applications using Large Language Models. You will develop AI agents and automated workflows that integrate with APIs, databases and tools, and optimize Retrieval-Augmented Generation pipelines.

With strong Python skills and expertise in backend frameworks, you will work across product, engineering, and clinical teams to advance AI-powered healthcare solutions.

Qualifications

• Proficient in Python with backend frameworks
• Hands-on experience building AI/LLM apps
• Experience integrating LLM APIs (OpenAI/Anthropic)
• Familiar with AI agents/workflows and tool calling
• Knowledge of RAG, embeddings, and vector DBs
• Understanding of AI evaluation, testing, and prompt safety
• Experience with AWS, Docker, and CI/CD pipelines
• Knowledge of security, data privacy and responsible AI practices
• Able to design RESTful APIs and backend services

Responsibilities

• Design, build, and deploy scalable AI applications using LLMs and modern frameworks
• Create AI agents and automated workflows that integrate with APIs, databases, and tools
• Develop and optimize Retrieval-Augmented Generation pipelines and vector stores
• Integrate LLM providers (OpenAI, Anthropic, AWS Bedrock) with prompt engineering
• Develop and maintain backend services and RESTful APIs for AI-powered apps
• Implement evaluation guardrails to ensure accuracy, safety, and data protection
• Optimize latency, token usage, and infrastructure costs
• Deploy and monitor AI services using cloud infra, Docker, and CI/CD
• Collaborate with product, engineering, and clinical teams to translate requirements
• Research new AI tech and continuously improve engineering practices

Skills

Python

AI agent workflows

LLM APIs

Problem solving

Security & privacy

CI/CD

Cloud/infra

Education

Degree in Computer Science or related field

Tools

LangGraph

LangChain

OpenAI

Anthropic

AWS Bedrock

Docker

FastAPI

Django

pgvector

Pinecone

Milvus

Job description

ThoughtFull is seeking an experienced AI/ML Engineer to design, build, and deploy scalable AI applications using Large Language Models. You will develop AI agents and automated workflows that integrate with APIs, databases and tools, and optimize Retrieval-Augmented Generation pipelines.

With strong Python skills and expertise in backend frameworks, you will work across product, engineering, and clinical teams to advance AI-powered healthcare solutions.