> Markdown version of [/jobs/ext/3676281-lead-ai-solutions-architect](https://www.wearedevelopers.com/jobs/ext/3676281-lead-ai-solutions-architect). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Lead AI Solutions Architect - **Company:** Genesys Telecommunications Laboratories, Inc. - **Location:** Menlo Park, CA, United States (Remote available) - **Experience:** Expert - **Salary:** $110,600.0 - $194,400.0 - **Contract:** Permanent contract - **Skills:** Training Data, Application Programming Interfaces (APIs), Artificial Intelligence, Data Cleansing, Python (Programming Language), Machine Learning, Natural Language Processing, Node.Js, Operational Databases, Performance Tuning, Strategies of Testing, Chatbots, Genesys, Large Language Models, Prompt Engineering, Generative AI, Agentic-AI, Build Management, Information Technology, Virtual Agents, Natural Language Understanding - **Published:** October 10, 2026 - **Apply:** https://diversityjobs.com/career/18594737/Lead-Ai-Solutions-Architect-California-Menlo-Park ## About the Role * Bring a master's degree in Computer Science, Data Science, Machine Learning, or a related technical field. * Demonstrate 3 to 5 years of experience working with conversational AI, generative AI, NLU, NLP, or related language technologies. * Apply Python and Node.js experience to data preparation, analysis, evaluation, automation, and model tuning. * Demonstrate experience working with Genesys Cloud, another CCaaS platform, or a conversational AI platform. * Apply hands-on experience developing, evaluating, or optimizing NLU models and LLM-based conversational experiences. * Analyze complex conversational AI performance issues and translate findings into actionable improvements. * Present technical findings, recommendations, and performance results clearly to customers and stakeholders. * Work independently while collaborating effectively with engineering, product, customer-facing, and other cross-functional teams., * Bring hands-on experience with prompt engineering and evaluation techniques for LLM-powered or agentic AI systems. * Demonstrate experience analyzing production conversation data and improving post-launch conversational AI performance. * Apply experience with evaluation frameworks, test-set development, experimentation, or performance measurement for AI systems. * Communicate professionally in Spanish in addition to English ## Description Agentic Virtual Agent Configuration and Tuning * Design and develop prompts for Agentic Virtual Agents that drive reliable task completion and high-quality customer experiences. * Structure prompts to support appropriate grounding, tool and API usage, orchestration, and response consistency. * Analyze failures in LLM-driven interactions and identify root causes across prompts, orchestration, data, and system behavior. * Refine prompts iteratively to improve reliability, edge-case handling, task completion, and user experience. * Evaluate end-to-end performance across NLU and LLM layers and implement data-driven optimizations. * Establish and apply evaluation frameworks and test methodologies that support continuous improvement of agentic systems. NLU Development * Design and build NLU models, including intents, entities, and utterances, that reflect real user behavior and business requirements. * Define scalable intent taxonomies and entity structures that support model accuracy, maintainability, and future growth. * Create and curate high-quality training data to improve model coverage, precision, and accuracy. * Translate customer requirements and conversation patterns into effective conversational AI designs. NLU Analysis and Optimization * Analyze production conversation logs to identify misclassifications, false positives, coverage gaps, and edge cases. * Optimize post-launch NLU performance through updates to training data, intent structures, and entity recognition. * Develop and execute scripts that support analysis, evaluation, and efficient implementation of NLU model improvements. * Measure and track NLU performance using defined evaluation metrics, test sets, and production data. * Communicate performance findings, recommendations, and measurable improvements to customers and internal stakeholders., * A Talent Acquisition Partner will review your application and, if your background is aligned, schedule a Zoom interview. * Next, you'll meet the hiring manager and other members of the interview team. * We aim to keep the process focused and respectful of your time, with no more than five interviews in most cases. * After interviews are complete, our team will follow up with the final steps. Every application is reviewed by a person. Response times may vary by role and location, but our team will keep you informed throughout the process. Stay Connected Stay connected to learn more about how we're applying AI to customer and employee experience challenges and get notified when relevant opportunities become available. Get notified about relevant opportunities. Be the one building what's next - where AI, experience and impact come together.