Forward-Deployed AI Solution Architect

5+ years of experience and proven track record in product management or solution architect roles Strong communicator with the ability to influence and collaborate across all levels Hands-on experience with agentic design and prompt engineering + architecture Strong coder with demonstrated proficiency in programming languages such as Python, Java, C++, TypeScript/JavaScript, or similar A go-to expert on emerging LLM technologies High customer empathy and passion for real-world impact and solving meaningful problems Self-starter, confident in troubleshooting complex systems issues independently Ability to work with a high level of autonomy and responsibility in a rapidly changing environment with dynamic objectives and iteration with users Demonstrated ability to collaborate effectively in teams of technical and non-technical individuals, and comfortable working in a rapidly changing environment with dynamic objectives and iteration with users Ability to travel as needed to client sites (expected 25-50%)

Develop deep understanding of client context and Qventus capabilities to identify high-leverage opportunities for rapid impact with bespoke AI Operational Assistant workflows Responsible for the design, execution, and optimization of bespoke AI Operational Assistant use cases at the client Leverage LLM-based AI (GPT, Claude, Gemini, LLaMA, etc.) to build advanced conversational systems Apply conversation modeling techniques like state machines, decision trees, and graph-based flows Use frameworks such as Dialogflow, Rasa, Amazon Lex, Langchain, or similar tools Collaborate with backend teams to integrate bots with APIs, CRMs, and enterprise systems Enhance bot functionality with custom scripts, API calls, and external system integrations Continuously tune and improve intent recognition and response quality using real user data Monitor and resolve conversation breakdowns, mismatches, and fallback issues Develop and run unit, regression, and A/B tests to ensure conversational performance Implement real-time monitoring, analytics, and logging to drive performance insights Shape client use cases in partnership with the AI Solution Consultant Collaborate closely with Qventus architects, engineers, and data scientists, as well as client end-users and IT teams to define and refine product requirements Work closely with software engineers and data scientists to refine LLM integration and behavior Document conversation logic, prompt structures, and decision workflows for scalability and maintainability Mentor and support cross-functional teammates across forward-deployed client team