AI Engineer
ThoughtFull World1 day ago
Kuala Lumpur, MalaysiaMid Level / Senior
Responsibilities
- Design, develop, and deploy scalable production AI applications using LLMs and modern AI frameworks.
- Build AI agents and automated workflows integrating APIs, databases, tools, and existing systems.
- Develop and optimize RAG pipelines involving document processing, embeddings, vector search, and retrieval strategies.
- Integrate and manage OpenAI, Anthropic, AWS Bedrock, and similar LLM providers using prompting, structured outputs, and function calling.
- Develop backend services and RESTful APIs for AI-powered applications and integrations.
- Implement AI evaluation frameworks, automated testing, guardrails, hallucination mitigation, prompt-injection protections, and human escalation mechanisms.
- Optimize AI application performance, latency, token usage, reliability, and infrastructure costs.
- Deploy, monitor, and maintain AI services using cloud infrastructure, Docker, and CI/CD pipelines.
- Collaborate with product, engineering, and clinical teams to deliver AI-powered solutions and evaluate emerging AI technologies.
Requirements
- A degree in Computer Science, Engineering, or a related field is required.
- At least 4 years of professional software engineering experience, including practical experience building AI/LLM applications.
- Strong Python and backend development skills, including FastAPI or Django.
- Hands-on experience integrating LLM APIs and building production-oriented applications with prompting, structured outputs, and tool or function calling.
- Experience with AI agents, agentic workflows, agent harnesses, tool orchestration, feedback loops, state management, and iterative execution.
- Understanding of RAG architectures, embeddings, retrieval techniques, and vector databases such as pgvector, Pinecone, or Milvus.
- Experience designing RESTful APIs, integrating databases, and developing backend services.
- Hands-on AWS, Docker, and cloud infrastructure experience, plus familiarity with Git, CI/CD pipelines, and application monitoring.
- Knowledge of application security, data privacy, responsible AI, AI evaluation, automated testing, hallucination mitigation, and prompt-injection risks.
- Ability to independently deliver AI features from prototype to production and communicate proficiently in English.
- Preferred: AWS Bedrock and cloud-native AI service experience; multi-agent systems and workflow orchestration; LangSmith, Langfuse, or similar observability and evaluation tools; speech-to-text, real-time conversational AI, or voice agents; model fine-tuning, selection, and inference optimization; machine learning, NLP, and transformer architectures; sensitive healthcare or regulated-environment experience; and healthcare, mental health, or personalized recommendation systems experience.
Benefits
- Hybrid full-time role based in Kuala Lumpur, Malaysia.
- Must be able to work Malaysia/Singapore time, GMT+8.
- The employer is unable to offer visa sponsorship at this time.