Platform Engineer
careerxtra- Posted 14 hours ago
- Be among the first 10 applicants
Job Description
We are working with an established company that is building and expanding its own AI platform and is looking for a talented Platform Engineer to join the team in Bangkok.
This is a hands-on opportunity for an engineer who wants to work with LLMs, RAG, AI agents, GPU infrastructure and AI security, while helping build production-ready AI solutions used by employees across the business.
PositionPlatform Engineer
Location: Bangkok, Thailand
Work Model: Hybrid
Employment Type: Full-time
Key Responsibilities- Develop, maintain and improve AI agents used by employees across different business functions, including onboarding users, integrating new tools, troubleshooting and gathering feedback.
- Continue developing the company's AI Gateway, including adding data sources, implementing OPA policies, improving retrieval capabilities and maintaining audit logs.
- Apply default-deny and least-privilege principles to AI systems and access controls.
- Improve the RAG pipeline by ingesting new documents, enhancing embedding and retrieval quality, classifying data sensitivity and measuring answer accuracy.
- Maintain and optimise LLM serving infrastructure, including vLLM/Ollama running on GPU servers.
- Evaluate and test new AI models while managing context lengths, memory requirements and performance.
- Integrate external AI APIs responsibly, considering API keys, costs, rate limits and security.
- Build automated AI workflows for business teams, such as report summarisation, customer support assistance and data analysis.
- Take AI projects from proof of concept through production, including design, development, testing, deployment and post-launch support.
- Monitor usage and performance metrics for AI solutions and report progress consistently.
- Create technical documentation and train employees to use AI tools effectively and safely.
- 2+ years of programming experience, with strong proficiency in Python.
- Comfortable working in Linux and command-line environments.
- Fluent in English, both written and spoken.
- Hands-on experience building real-world applications with LLMs, beyond simply using ChatGPT.
- Practical experience with one or more of the following:
- LLM APIs
- RAG systems
- AI agents and tool calling
- Fine-tuning
- Strong understanding of LLM fundamentals, including tokens, context windows, embeddings, prompt engineering, hallucinations and mitigation techniques.
- Understanding of AI security, including prompt injection, data leakage and the importance of authorisation layers between AI systems and company data.
- Experience using AI-powered coding tools such as Claude Code, Codex, GitHub Copilot or similar as part of your development workflow.
- Strong problem-solving skills and the ability to quickly understand unfamiliar systems, codebases and documentation.
- Comfortable taking ownership of projects from development through deployment and ongoing support.
- Hybrid working model in Bangkok.
- Attractive remuneration based on experience and technical skill set.
- Hands-on experience with GPU infrastructure, real-world AI models and production AI systems.
- The opportunity to work on an AI platform used by real users across the business.
- A clear growth path towards becoming the Lead Engineer responsible for the company's AI platform.
- A highly practical environment where you can experiment, build and see your work move into production.
- And more.
If you're passionate about building practical AI systems and want to work beyond simply integrating existing AI tools, we'd love to hear from you.
More Info
Key Skills
GitHub Copilot
AI agents and tool calling
GPU infrastructure
LLM APIs
LLMs
RAG systems
Codex
Claude Code
AI security
Fine-tuning





