Skip to main content
ContractRemote50,000 THB/mo

AI Engineer

AI / Machine Learning · Remote — Work From Anywhere

Apply now

About iReadCustomer

iReadCustomer is a leading DataTech startup and AI software house specializing in Data Analytics, Custom AI Agents, Workflow Automation, and Digital Transformation — the engineering powerhouse behind 50+ enterprise platforms across Southeast Asia.

We're hiring a skilled AI Engineer specializing in LLMs and Generative AI who thrives on end-to-end execution — from interpreting business logic and designing complex RAG/Agent architectures to writing clean code and serving scalable APIs.

What you’ll do

  • Design & build robust Custom AI Agents, RAG (Retrieval-Augmented Generation) pipelines, and automated AI workflows for complex business use cases.
  • Architect complex agentic workflows with frameworks like LangGraph.
  • Run prompt engineering, strict model evaluation, and fine-tuning for accuracy, performance, and minimal hallucination.
  • Build & maintain data ingestion, context handling, and memory pipelines optimized for vector databases.
  • Collaborate with full-stack teams to integrate AI models into production via robust APIs.
  • Self-manage end-to-end delivery on schedule with exceptional engineering quality.

Tech stack

Python · TypeScript · LangChain · LangGraph · MCP (Model Context Protocol) · LlamaIndex · OpenAI / Anthropic APIs · Vector Databases (Qdrant) · Neo4j · FastAPI

Compensation & perks

  • Base: up to 50,000+ THB/month (by skill & experience).
  • Project Success Bonus: an uncapped incentive every time you ship a client project on schedule.
  • 99% Work From Anywhere — full flexibility, contingent on code quality & milestones.
  • AI tooling budget — company-covered subscriptions for your preferred AI ecosystems.

How to apply

Apply directly using the form below. You can also reach us at [email protected] or 085-990-8320.

What we’re looking for

  • Extreme ownership & self-driven delivery: scope, drive, and ship client projects independently
  • Deep AI/LLM expertise: operational + architectural grasp of LLMs, advanced RAG pipelines, contextual memory, and agentic workflows (especially LangGraph)
  • Strong Python & TypeScript engineering: scalable, high-performance APIs and integrations for AI deployment
  • Data & AI architecture sensibility: meticulous data preparation and rigorous AI evaluation for production-grade reliability
  • Hands-on with vector databases and prompt engineering

Apply for this role

Fill in your details and attach your CV. We review every application.

PDF, DOC or DOCX · max 5 MB