The AI Engineer builds production agents end-to-end on an AI-native retail decisioning platform — prompt design, tool definitions, multi-step workflows on the agent runtime (LangGraph, CrewAI, or chosen framework), evaluation harnesses (golden sets, regression gates, multi-step replay), human-in-the-loop gate integration, and per-agent cost optimisation. The role consumes platform-provided LLM and vector services; it does not rebuild that platform. 

Remote candidates outside of Thailand are welcome to apply.

Key Responsibilities:

• Build agents on the platform's agent runtime — prompt design, tool definitions, multi-step workflows, error handling — and ship them with eval harness, human-in-the-loop gate config, observability instrumentation, cost meter, and runbook. 
• Co-design agent specs with Tech Lead Applications and Suite Product Owners; partner with ML Engineers on classical ML model integration into agents. 
• Author golden sets per agent — domain-specific test cases capturing must-pass behaviours; build regression gates in CI so no agent ships without eval-pass. 
• Implement multi-step conversation replay for agents with stateful interactions; use LLM-as-judge patterns where appropriate; instrument human feedback collection. 
• Configure HITL gates per agent and per agent plan; implement gate-progression evidence collection (Shadow data, accuracy metrics, override frequency). 
• Own per-agent cost meter — tokens, vector queries, model inference; report monthly; tune model routing and implement caching strategies where appropriate. 
• Consume the enterprise LLM Gateway via standard SDK; partner with platform AI engineering on embedding model selection and retrieval relevance tuning. 
• Mentor seed-programme engineers and contribute to the agent-engineering playbook. 

Requirements

• Bachelor's or Master's degree in Computer Science, AI / ML, or a related discipline. 
• 5+ years software engineering with 2+ years shipping LLM-based or agentic systems to production. 
• Production agent or multi-step LLM workflow experience — LangGraph, CrewAI, AutoGen, DSPy, or custom. 
• Strong Python; comfortable with async, observability, testing. 
• Hands-on with at least one major LLM provider (Azure OpenAI, Anthropic, Bedrock, Vertex). 
• Eval-driven LLM development — golden sets, LLM-as-judge, regression gates, multi-step replay. 
• HITL gate / agent governance — has shipped agents with explicit gates, not autonomous-by-default. 
• Prompt injection / data leakage / PII handling — designs and tests defences. 

Preferred Qualifications

• Open-source contributions to agent frameworks (LangChain / LangGraph / DSPy). 

• Multi-agent system at scale in production; retail / commerce / fintech agentic workflows (supplier onboarding, contract intelligence, comparable). 

• Causal inference exposure (DoWhy / EconML); Thai-language NLP (PyThaiNLP, WangchanBERTa, SEA-LION, Typhoon). 

• Vendor certifications such as Databricks Generative AI Engineer or Azure AI Engineer Associate.