LLMs & GenAI-Agent Expert - Hà Nội - TA139

Laptop, Insurance, Travel opportunities, Allowances, Uniform, Incentive bonus, Health checkup, Training & Development, Salary review, Seniority Allowance, Annual Leave, Sport Club

About VPBank - AI Center

VPBank is at the forefront of innovation in banking and financial sector, leveraging cutting-edge technologies to transform our internal operations, banking, and financial products, and to deliver exceptional values to our customers. AI Center of VPBank, led by Dr. Dao Huu Hung, is building a dedicated team to develop and deploy large-scale Generative AI (GenAI) Agent-based internal banking and financial products, providing unique opportunity to work on projects that are both challenging and impactful. We offer unparalleled access to real-world and large-scale data and the chance to build solutions that directly influence the core banking and financial processes.

We are seeking highly skilled and passionate LLMs & GenAI Agent Engineers to join our dynamic team. You will be responsible for designing, developing and deploying advanced GenAI Agents with a specific focus on multi-agent systems to automate and optimize the workflows. This role demands deep expertise in LLMs, agent orchestration, and cloud-based deployment, particularly on Databricks and AWS Bedrock. You will play a pivotal role in building intelligent, autonomous systems that streamline, automate and optimize workflows, and drive innovation in VPBank.

Key Responsibilities

• Designing, implementing and optimizing multi-agent systems using LLMs and GenAI technologies
• Integrating and finetuning LLMs with data sources using RAG, Deep Search, and Deep Think techniques.
• Data integration and management: work with large-scale and dynamic banking and financial datalake house, ensuring seamless integration and efficient data processing within agent workflows.
• Cloud deployment and scalability: deploy and manage GenAI agent systems on cloud platforms, primarily DataBricks, ensuring scalability, reliability, and security.
• Agent orchestration and tool usage: develop and implement robust agent orchestration frameworks, enabling agents to effectively utilize various tools and APIs.
• Prompt engineering and optimization: Craft and optimize prompts to maximize the performance and accuracy of LLMs and agents.
• Evaluation and Monitoring: design and implement metrics for evaluating agent performance, continuously monitor and optimize deployed systems.
• Collaboration and knowledge sharing: collaborate with cross-functional teams, including data scientists, software engineers, IT system engineers, and business stakeholders, and contribute to knowledge sharing and best practices.
• Research and innovation: stay up-to-date with latest advancements in LLMs and GenAI, and contribute to research and innovation initiatives.
• Collaborating with teams and upholding AI ethics, privacy, and security, especially for financial compliance.