Lead GenAI Engineer

Trimble Inc. is a technology company that specializes in transforming the way the world works. They are seeking a Lead GenAI Engineer to design, implement, and test software applications, specifically focusing on LLM-based agents while working in a cross-functional team.

Responsibilities:

• Work in a cross-functional team with product managers, user experience designers and other software developers
• Work in an agile environment, planning and executing sprints, meeting strict deadlines, and efficiently handling production issues across multiple time zones
• Contribute knowledge and experience to the continuous development and improvement of our platform and drive sharing
• Act as a senior advisor using experiences to lead colleagues, train juniors
• Ensure security, data integrity and data protection aspects
• Creation of documentation
• Debug and resolve technical issues; act as 3rd level support
• Drive to translate high-level product requirements into scalable, modular software designs that adhere to modern design principles, microservices architecture, and cloud-native best practices
• Architect Generative AI-based features leveraging Large Language Models, RAG frameworks, MPC or agent orchestration. Implement them, including leading team members
• Continuously engage in professional development and keep track of latest research, given that this is a fast evolving field
• Develop comprehensive test suites (unit, integration, and end-to-end) to ensure code quality and ensure that automated tests cover a high percentage of the codebase
• Implement/Architect CI/CD pipelines and maintain code versioning in Git for seamless, frequent releases
• Monitor performance, including services for LLM features such as Datadog and Databricks. Identify performance bottlenecks and support to resolve them

Requirements:

• Analyses, designs, programs, debugs, and modifies software enhancements and/or new products used in local, networked, cloud-based or Internet-related computer programs
• Code may be used in commercial or end-user applications, such as materials management, financial management, HRIS, mobile apps or desktop applications products
• Using current programming language and technologies, writes code, completes programming, and performs testing and debugging of applications
• Completes documentation and procedures for installation and maintenance
• May interact with users to define system requirements and/or necessary modifications
• Design, implementation and testing of software applications including LLM-based agents using the Transporeon technology stack
• Work in a cross-functional team with product managers, user experience designers and other software developers
• Work in an agile environment, planning and executing sprints, meeting strict deadlines, and efficiently handling production issues across multiple time zones
• Contribute knowledge and experience to the continuous development and improvement of our platform and drive sharing
• Act as a senior advisor using experiences to lead colleagues, train juniors
• Ensure security, data integrity and data protection aspects
• Creation of documentation
• Debug and resolve technical issues; act as 3rd level support
• Drive to translate high-level product requirements into scalable, modular software designs that adhere to modern design principles, microservices architecture, and cloud-native best practices
• Architect Generative AI-based features leveraging Large Language Models, RAG frameworks, MPC or agent orchestration
• Implement them, including leading team members
• Continuously engage in professional development and keep track of latest research, given that this is a fast evolving field
• Develop comprehensive test suites (unit, integration, and end-to-end) to ensure code quality and ensure that automated tests cover a high percentage of the codebase
• Implement/Architect CI/CD pipelines and maintain code versioning in Git for seamless, frequent releases
• Monitor performance, including services for LLM features such as Datadog and Databricks
• Identify performance bottlenecks and support to resolve them