Senior Data Scientist We are looking for a Senior Data Scientist to join our AI Data Science team and contribute to the development and continuous improvement of Generative AI capabilities across our Contact Center and Unified Communications products. You will work on challenging problems involving Large Language Models, retrieval, agent behavior, experimentation, evaluation, and optimization. Your work will help create AI agents that understand customer needs, access relevant knowledge, use tools effectively, and successfully complete complex tasks. This is a hands-on role focused on applying, integrating, and evaluating provider-hosted LLMs rather than developing foundation models in-house. You will work closely with software engineers, AI/ML engineers, product managers, domain experts, and other data scientists to take GenAI solutions from experimentation through production. You will independently handle complex assignments and make sound technical decisions when requirements or expected behavior are not fully defined. The role focuses on technical execution and collaboration within established product and platform priorities, without responsibility for managing people or leading broader organizational initiatives. What You'll Do: • Typically 8 years of professional experience in data science, applied AI, machine learning, software engineering, or a related field, including meaningful hands-on experience with Generative AI. • Develop, evaluate, and continuously improve GenAI solutions that power Intermedia’s AI Platform and other AI-enabled products. • Improve agent behavior across reasoning, tool selection and execution, knowledge retrieval, context management, personalization, and multi-step task completion. • Design and optimize prompts, structured instructions, context-building strategies, structured outputs, and other LLM interaction patterns. • Develop and optimize Retrieval-Augmented Generation solutions, including embeddings, retrieval strategies, ranking, semantic search, and context selection. • Experiment with models, prompts, retrieval strategies, agent instructions, tools, and configuration approaches to identify the solutions that deliver the best customer and business outcomes. • Define evaluation frameworks, metrics, benchmarks, test scenarios, and datasets that measure accuracy, relevance, task completion, reliability, safety, and customer experience. • Design offline and online experiments to compare GenAI approaches and determine whether changes produce meaningful improvements. • Identify and mitigate failure modes such as hallucinations, poor retrieval, inappropriate responses, inconsistent behavior, and unsuccessful tool execution. • Analyze production traces, agent behavior, evaluation results, and customer feedback to identify patterns, regressions, and improvement opportunities. • Collaborate with engineering teams to integrate GenAI components into scalable, reliable, secure, and observable production services. • Apply safeguards for responsible AI use, including grounding, output validation, privacy, security, and protection against prompt injection or unsafe behavior. • Experience with conversational or voice AI, LLM observability platforms, vector databases, or Contact Center and Unified Communications products is an advantage. • Strong Python programming skills and the ability to develop maintainable, tested, production-quality code.
