Type: Full-Time | Department: Engineering / AI Solutions | Location: Lat Krabang
About the Role We are looking for a mid-level fullstack engineer who is equally comfortable shipping web applications and building AI-powered features. You will design, develop, and integrate AI solutions from LLM and generative-AI applications to the APIs, data flows, and user interfaces that put them into production. This is a hands-on role for someone who enjoys owning features end to end, translating real business and research problems into working software, and staying close to a fast-moving AI landscape.
• Build and maintain fullstack web applications, covering responsive frontends, backend services, and well-designed APIs.
• Develop and integrate AI/LLM-powered features — chat interfaces, retrieval-augmented generation (RAG), agents, summarization, and document processing.
• Integrate third-party AI services and models (e.g. OpenAI, Anthropic, open-source LLMs) into products via APIs and SDKs.
• Design prompts, evaluation setups, and guardrails to make AI features reliable, accurate, and safe.
• Build data pipelines to prepare, store, and retrieve content for AI workloads, including vector databases and embeddings.
• Collaborate with product, design, and research teams to turn requirements into shippable solutions.
• Write clean, tested, maintainable code and participate in code reviews.
• Deploy and monitor applications in cloud environments, and help improve CI/CD and observability.
• 2–5 years of professional software engineering experience across the fullstack.
• Strong proficiency in a modern backend language (e.g. Python, Node.js/TypeScript, Go) and a frontend framework (e.g. React, Vue, or Next.js).
• Hands-on experience integrating LLMs or generative-AI APIs into real applications, including prompt engineering and handling model outputs.
• Solid understanding of REST/GraphQL APIs, relational and/or NoSQL databases, and authentication.
• Familiarity with RAG patterns, embeddings, and vector databases (e.g. pgvector, Pinecone, Weaviate, or similar).
• Experience with Git, containers (Docker), and deploying to a major cloud provider (AWS, GCP, or Azure).
• A pragmatic, product-minded approach and strong problem-solving and communication skills.
• Experience building or orchestrating AI agents and tool-use workflows (e.g. LangChain, LlamaIndex, or custom frameworks).
• Exposure to ML concepts — fine-tuning, model evaluation, or MLOps.
• Knowledge of streaming responses, WebSockets, or real-time systems.
• Contributions to open-source projects or a portfolio of AI-related work.