AI Engineer
Location:
Thailand - Bangkok, Thailand
Company:
Gulf Group
Job Responsibilities
1) End-to-End AI Development:
-Responsible for the complete entire AI development lifecycle from ideation, model/tool selection, implantation, testing and roll out including monitoring and optimization.
•Model Optimization: Fine-tune and optimize large-scale generative models (e.g., LLMs) using techniques like RLHF.
•Prompt Engineering: Design and manage advanced prompts to control and improve model output quality and safety.
•Data Curation: Curate high-quality datasets for model fine-tuning and building knowledge bases.
•RAG System Development: Build and maintain Retrieval-Augmented Generation (RAG) pipelines, including vector databases.
•Deployment & API Integration: Deploy models and develop scalable APIs for integration into applications.
•Evaluation & Safeguarding: Evaluate model performance and implement safeguards against issues like hallucination and bias.
2) Project Coordination & Communication:
-Communicate plans, status, risks and issues to project governance team and stakeholders in a timely manner, as well as escalate any potential issues where required.
-Serve as a single point of contact for some of the assigned applications.
-Provide training and system specification document of application to peers and to users where appropriate.
3) Technical Support & Improvement:
-Investigate and resolve application functionality related issues, provide 1st and 2nd support, troubleshooting and identify modification needed
-Learn new technologies, languages, and techniques so that you are able to adapt to the evolving needs of our business e.g. AI.
Job Qualifications
•Bachelor’s degree in AI, Data Science, computer science, engineering, IT or a related field from Prominent universities
•Creative individual with deep technological expertise in AI development & Cloud background
1) Programming & LLM Frameworks:
-Expert-level Python programming skills.
-Extensive, hands-on experience with LLM Frameworks ex. LangChain for building complex LLM-powered applications, including agentic workflows and chains.
2) Microsoft Azure
-Azure OpenAI Service: Expertise in deploying, fine-tuning, and managing foundational models (like GPT-4) within a secure Azure environment.
-Azure AI Search (formerly Cognitive Search): Proficiency in building RAG solutions by creating indexes and data sources to ground LLMs in private data.
-Azure AI Studio: Familiarity with the unified platform for building, evaluating, and deploying generative AI applications.
-Copilot Integration: Understanding of how to extend and integrate with Microsoft Copilots, bringing custom data and plugins into the Copilot ecosystem.
3) Google Cloud
3) Google Cloud
-Google Vertex AI Platform: In-depth knowledge of the Vertex AI suite for managing the generative AI lifecycle.
-Vertex AI Search and Conversation: Proven experience building sophisticated RAG-based search engines and conversational AI applications.
-Vertex AI Model Garden & Generative AI Studio: Skill in discovering, customizing, and deploying foundation models from Google and the open-source community.
-Vertex AI Pipelines: Ability to orchestrate and automate complex GenAI workflows, from data ingestion to model deployment.
•Good command in English (Minimum 750 TOEIC score).
•Goal-Oriented, Unity, Learning, Flexible.