01
About This Role
We're looking for an AI/ML Engineer to bring practical AI features into our products and client solutions, including LLM-powered assistants, retrieval systems, and predictive models. You'll prototype quickly, evaluate carefully, and ship AI that is reliable, measurable, and cost-aware.
02
What You'll Do
- Design and build LLM-based features: retrieval-augmented generation, tool use, and agents
- Build data pipelines for ingestion, chunking, embeddings, and vector search
- Create evaluation sets and automated evals to measure quality, safety, and regressions
- Train, fine-tune, or adapt classical ML models where they are the better fit
- Deploy models and AI services with monitoring for latency, cost, and output quality
- Work with product and engineering teams to find where AI adds real value
- Keep up with the field and share what you learn with the team
03
What We're Looking For
- 2+ years of experience building ML or AI systems in production
- Strong Python skills and experience with modern ML/AI libraries
- Hands-on experience with LLM APIs, prompt design, and retrieval systems
- Understanding of evaluation methods and common failure modes (hallucination, drift, bias)
- Experience with vector databases or search engines
- Ability to explain technical trade-offs to non-technical stakeholders
04
Nice to Have
- Experience with Thai-language NLP
- MLOps experience (model registries, feature stores, monitoring)
- Experience with GPU workloads and inference optimization
- Backend skills in Go or TypeScript
- Published research, blog posts, or open-source work