
ThoughtFull develops digital mental health services for employee wellbeing, combining preventive resources and therapeutic care in one app. Employees can connect with certified professionals for online therapy and access round-the-clock crisis support. The company works with insurers and organizations across Asia, using evidence-based care and measurable outcomes to help employers address workplace stress and strengthen workforce wellbeing. ThoughtFull’s team works across mental health, insurance, hospitality, and consulting.
AI Engineer (LLMs and RAG) — ThoughtFull, Malaysia
Build production LLM applications, AI agents, and retrieval-augmented generation systems for ThoughtFull’s mental healthcare platform. Deploy secure AI services and backend integrations on cloud infrastructure.
RM 8,300 – RM 13,300 / month
HybridFull-timeMiddleSeniorEnglish RequiredAI EngineerMachine Learning EngineerDescription
- Create scalable, secure AI applications with large language models and modern frameworks.
- Build agents and automated workflows that connect APIs, databases, tools, and existing systems.
- Develop and improve RAG pipelines, from document processing and embeddings to vector search and retrieval.
- Integrate LLM providers including OpenAI, Anthropic, and AWS Bedrock, using prompt engineering, structured outputs, and function calling.
- Build and maintain backend services and REST APIs.
- Create evaluation frameworks and safeguards for accuracy, safety, reliability, sensitive-data protection, and human escalation.
- Improve application performance, response times, token efficiency, and infrastructure costs.
- Deploy, monitor, and maintain AI services using cloud infrastructure, Docker, and CI/CD pipelines.
- Work with product, engineering, and clinical teams to turn business needs into AI-powered solutions.
- Assess emerging AI technologies, models, and frameworks.
Requirements
- Degree in computer science, engineering, or a related discipline.
- At least four years of professional software engineering experience, including hands-on development of AI or LLM applications.
- Proficiency in Python and backend frameworks such as FastAPI or Django.
- Practical experience integrating LLM APIs, including OpenAI, Anthropic, or similar services.
- Experience building production LLM applications with prompting, structured outputs, and tool or function calling.
- Hands-on experience with AI agents and agentic workflows, using LangGraph, LangChain, or comparable approaches.
- Understanding of RAG architecture, embeddings, retrieval methods, and vector databases such as pgvector, Pinecone, or Milvus.
- Knowledge of AI evaluation, automated testing, hallucination reduction, and prompt injection risks.
- Experience with agentic AI architectures, agent harnesses, and iterative execution loops, including tool orchestration, feedback loops, state management, and automated validation.
- Experience designing REST APIs, integrating databases, and developing backend services.
- Hands-on experience with AWS, Docker, and cloud infrastructure.
- Familiarity with CI/CD pipelines, Git, and application monitoring.
- Knowledge of application security, data privacy, and responsible AI practices.
- Strong problem-solving skills and the ability to deliver AI features independently from prototype through production.
- Availability to work in Malaysia or Singapore time (GMT+8).
- Fluent English, with strong written and verbal communication skills.
- Visa sponsorship is unavailable.
Related Jobs
No jobs found
Try adjusting or clearing your filters to find more opportunities.