About the Role
We are seeking an innovative and hands-on AI Engineer with experience in building LLM-powered applications using frameworks such as LangChain, LLamaIndex, and agentic frameworks such as LangGraph, CrewAI etc.
In this role, you will develop intelligent, autonomous agents capable of reasoning, decision-making, and multi-step task execution. You will integrate these agents into our digital platforms to solve complex problems across domains such as customer support, knowledge discovery, automation, and data analysis.
Key Responsibilities
- Design and implement agent-based architectures using frameworks like LangGraph, CrewAI, Agno, or similar to orchestrate LLM behavior in multi-step workflows.
- Develop prompt engineering strategies, memory management, and agent coordination logic to ensure reliability and performance of AI agents.
- Build composable AI workflows by chaining tools, APIs, and third-party services that agents can invoke securely and intelligently.
- Integrate LLM agents into enterprise products and digital interfaces (e.g., chatbots, data pipelines, workflow automation tools).
- Collaborate with product teams to define use cases and translate them into autonomous agent workflows with measurable outcomes.
- Implement observability for agent behavior (e.g., traceability, tool usage logs, fallback flows).
- Ensure responsible AI practices, including guardrails, rate limiting, sandboxing, and human-in-the-loop design for critical agent actions.
- Drive innovation by experimenting with new LLMs (e.g., GPT-4o, Claude, Gemini) and fine-tuning or RAG-based enhancement strategies.
Required Skills & Qualifications
- Bachelor’s or Master’s in Computer Science, AI, Machine Learning, or equivalent.
- 3+ years of experience in AI engineering or ML development, with at least 1 year in LLM-based system design.
- Proficiency in Python, with strong experience in frameworks such as LangGraph, CrewAI, Agno, LangChain, or AutoGen.
- Deep understanding of prompt engineering, tool integration, and LLM orchestration patterns.
- Solid knowledge of RESTful APIs, vector databases (e.g., Pinecone, FAISS, Weaviate), and retrieval-augmented generation (RAG).
- Familiarity with hosting and serving LLMs via Azure OpenAI, open-source models (Mistral, LLaMA2), or self-hosted inference servers.
- Experience with Docker, Kubernetes (AKS), and CI/CD pipelines for deploying AI agents at scale.
- Strong collaboration skills with an ability to work cross-functionally in agile product environments.
Good to have
- Prior implementation of multi-agent AI systems (negotiation, task planning, reflection, delegation).
- Experience with LangGraph for memory and stateful workflows, or Agno for domain-driven agent design.
- Understanding of LLMOps, vector search optimization, and embedding strategies.
- Knowledge of agent governance, safety constraints, and explainability in autonomous AI behavior.
- Certifications in Microsoft Azure AI, OpenAI ecosystem, or advanced prompt engineering.
Pay: From RM5,000.00 per month
Benefits:
- Additional leave
- Health insurance
- Maternity leave
- Opportunities for promotion
- Parental leave
- Professional development
Ability to commute/relocate:
- Petaling Jaya: Reliably commute or planning to relocate before starting work (Preferred)
Application Question(s):
- Minimum 3 years of experience in AI engineering or ML development is required. Do you meet this requirement?
Education:
Experience:
- ML development: 3 years (Required)
License/Certification:
- Microsoft Azure AI (Required)
Work Location: In person