Search by job, company or skills
We are seeking a skilled professional to design, develop, and deploy scalable LLM and agent-based AI solutions for thousands of users. You will architect multi-agent workflows, build robust APIs and RAG pipelines, and deliver advanced multimodal features. The role requires expertise in frameworks such as LangChain, LangGraph, and OpenAI Agents SDK, as well as strong skills in machine learning and database integration. You will drive innovation by optimizing system performance and collaborating to deliver production-ready AI systems.
Key ResponsibilitiesArchitect and implement agent workflows utilizing frameworks such as LangChain, LangGraph, or the OpenAI Agents SDK.
Design multi-agent system, utilizing tools/model-context-protocol (MCP).
Develop high-performance RESTful and streaming APIs using FastAPI.
Design, build, and evaluate RAG pipelines leveraging enterprise-grade vector databases.
Deliver multimodal LLM features integrating text, vision, speech, and structured data.
Instrument and monitor key metrics, including latency, cost, and hallucination rates.
Apply core machine learning, deep learning, and Transformer-based algorithms to optimize and troubleshoot models.
Design relational database schemas, write optimized SQL, and integrate transactional data sources.
Minimum QualificationsBachelors degree in Computer Science, Data Engineering, or a related field.
Minimum of 2 years experience building and operating ML/AI systems in production environments.
Hands-on experience with at least one agent framework (e.g., LangChain, LangGraph, OpenAI Agents).
Proven track record in delivering RAG solutions, including indexing, retrieval optimization, and evaluation.
Proficiency in Python and experience with FastAPI.
Familiarity with multi-agent system with tools/model-context-protocol (MCP).
Demonstrated experience with multimodal LLM projects.
Strong foundation in machine learning fundamentals, deep learning architectures, and Transformer internals.
Expertise in relational database design and advanced SQL.
Effective communication skills in English (B2 level or higher).
Nice to haveProficiency with AI coding assistants and IDE extensions (e.g., Claude, Cursor, Windsurf) to accelerate development workflows.
Experience with containerization and orchestration tools such as Docker and Kubernetes.
Practical experience running models locally using vLLM or Ollama.
Proficiency in Japanese communication.
BenefitsFPT Care health insurance provided by PJICO, exclusive for FPT employees
Annual summer vacation starting from May, following company policy
Annual salary review
International, dynamic, and collaborative working environment
Annual leave and working conditions compliant with Vietnam labor laws
Support for international certification exams and study sponsorship
Loan interest support policy for Fsofter employees
Shuttle bus service for employees
Date Posted: 06/09/2025
Job ID: 125596115