Tìm việc làm IT

ABOUT THE JOB

• Design, develop, and implement end-to-end AI agent systems, from solution architecture and knowledge integration to deployment and production monitoring.
• Build agentic AI and multi-agent workflows capable of planning, reasoning, context management, tool execution, and structured response generation.
• Develop reliable LLM applications using prompt engineering, function calling, structured outputs, fallback mechanisms, and AI guardrails.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines, including embedding generation, semantic search, document processing, and vector retrieval.
• Integrate AI agents with external APIs, backend services, and enterprise workflows through scalable REST APIs and asynchronous or event-driven architectures.
• Develop AI services using Python and frameworks such as FastAPI, LangChain, LangGraph, and Hugging Face Transformers.
• Optimize AI solutions for response quality, latency, scalability, inference cost, and production stability through evaluation, caching, workflow optimization, and monitoring.
• Deploy and maintain AI models and services in containerized and cloud-based environments, using technologies such as Docker, Microsoft Azure, and Linux.
• Collaborate with backend, product, and cross-functional teams to integrate AI capabilities into reliable, user-focused solutions.
• Document technical solutions, contribute to engineering best practices, and support continuous improvement of AI platforms and workflows.

ABOUT YOU

• Bachelor’s or Master’s degree in engineering, artificial intelligence, machine learning, or a related technical field, or have equivalent practical experience.
• 3+ years of experience in AI/ML engineering, with hands-on experience delivering AI solutions from development through production.
• Have practical experience designing and implementing LLM applications, AI agents, agentic workflows, or multi-agent systems.
• Demonstrate strong knowledge of RAG, prompt engineering, function calling, structured output generation, context management, semantic search, and embedding pipelines.
• Have hands-on experience with Python and AI frameworks or tools such as LangChain, LangGraph, Hugging Face, and Transformers.
• Have experience building backend services and APIs using FastAPI, REST APIs, AsyncIO, or similar technologies.
• Have experience working with vector databases and data-storage technologies such as Qdrant, Redis, MongoDB, MySQL, or knowledge graphs.
• Understand AI model evaluation, inference optimization, deployment, monitoring, and reliability practices.
• Have experience with Docker, Linux-based development environments, and cloud platforms such as Microsoft Azure.
• Are comfortable working with asynchronous workflows, distributed systems, event-driven architectures, or AI workflow orchestration.
• Demonstrate strong problem-solving, communication, collaboration, adaptability, and attention to detail.
• Have good English communication skills and the ability to work effectively with cross-functional teams.

WHY AMARIS?

• Competitive salary and 13th-month salary
• 14+ annual leave days per year
• Premium healthcare insurance starting from your probation period
• Regular project reviews and yearly performance appraisal
• Annual company trip
• Team-building activities: team lunch/dinner, events and celebrations, sports clubs (football, basketball, badminton, pickleball)
• International working environment
• Tailor-made career path and clear growth opportunities
• Technical workshops and training courses (internal & external)
• Mobility opportunities to work on-site in our offices in 60+ countries

Equal Opportunity

Amaris Consulting is proud to be an equal opportunity workplace. We are committed to promote diversity within the workforce and creating an inclusive working environment. For this purpose, we welcome applications from all qualified candidates regardless of gender, sexual orientation, race, ethnicity, beliefs, age, marital status, disability, or other characteristics.

#LI-DL5