Lead GenAI Engineer, Tricentis

• 7 years of experience with Python
• 5 years of experience with NLP, Classical AI, machine learning or data science
• 1 year of experience working with and deploying language model based solutions
• 5 years of experience working with cloud AI platforms
• Strong knowledge of LangChain, LangGraph, or similar frameworks for building modular AI systems
• Experience working with leading Agent frameworks
• Proven experience working with agent evaluation frameworks in production
• Production Experience:
• Good understanding of software engineering best practices, including version control, CI/CD, and testing
• Experience creating development best practices and standards
• Familiarity with data pipelines and data management techniques
• Production experience with distributed tracing
• Strong understanding of security and compliance standards within DevOps/SRE environments
• Experience working with and developing in containers, including management and deployment in production
• Cloud Platform Affinity:
• Experience working with AWS AI Foundry, Amazon Bedrock or similar
• Experience working on AWS and Azure environments for cloud training
• Strong experience with containerized deployment environments
• Understanding of cloud data storage, caching, networking and its relationship to AI products
• Track record of Success:
• Proven competence in delivering results for your organisation
• Evidence of high level of influence in identified projects, resulting in significant value for your company
• Soft Skills:
• Proven ability to run team meetings, and communicate effectively to product and business people
• Must be comfortable working directly with customers and support

• As Lead GenAI Engineer you will be working on a team of highly skilled engineers and researchers, focused on bringing technologies in the space of Agentic AI and unstructured data access to bear in Tricentis’s strategic technology pipeline
• You will work with and lead an engineering team, ensuring that Tricentis customers are provided with the highest quality, most advanced QA AI agents possible
• Your role within this initiative will be to be to work with technology leaders and product leaders to execute on our highest priority AI workstream
• You will be at the forefront of adopting new technologies, assist in setting patterns for the research team, and linking product problems to agentic solutions
• You will be responsible for implementing evaluation frameworks, agentic action models, recommending model training to our data science team, creating policies and communicating to internal and external stakeholders our AI technology strategy
• Industry Knowledge:
• Contribute to Tricentis’ technical strategy and approach with regard to the implementation of agent frameworks (such as AutoGen, Langgraph, Crew.AI or similar)
• Contribute to Tricentis’ technical strategy for unstructured data search techniques (Vector DBs, Reranking, Knowledge Graphing, GraphRAG) or similar
• Gather current leading techniques from industry and communicate how they impact our strategy, or not
• Leadership and Mentoring:
• You will be responsible for implementing standards, motivating the team and providing a role model for upcoming engineers to aspire to
• You will review the code and approaches of other staff, and provide encouraging, constructive feedback to improve their work product, and enhance their engagement
• You will interview new staff and provide feedback to the recruiting loop, and the candidate
• You actively involve yourself in corporate events, volunteering for speaking or presentation engagements, seeking opportunities to share your knowledge
• Applied Research
• You will be responsible for working with product teams to identify if agentic AI solutions can address business problems, outline the path to a solution and assist in prioritizing the workstream
• You will run implementation teams, ensuring that the work committed is consistently advancing the business problems and our technical strategy
• You will ensure standards and guidelines for implementation teams are followed
• You will ensure effective use of evals, and promote good AI architecture to enhance testability and transparency of the models
• You will advance and enforce our AI safety and responsible development practices

Total funding: $1.5bn

In a traditional software development cycle, developers would take months to create and deliver a product. Testing involved writing scripts to test all the different parts of the program, and when the software changed, it usually broke the scripts and triggered a lot of time-consuming manual fixing.