The Right Model for the Right Job: Cutting LLM Costs Without Cutting Quality
Most AI agents never make it past the demo stage, and the gap between a prototype and a production system comes down to evaluation. I cover how to choose between open source, proprietary, and fine-tuned models, define custom metrics for your use case, calibrate LLM judges for cost-effective assessment, and track results over time to measure real progress. Attendees leave with practical tools to move from proof-of-concept to production.
Key Takeaways:
How to choose between open source, proprietary, and fine-tuned models for your use case.
Defining custom evaluation metrics that reflect what quality means for your application.
Calibrating LLM judges for cost-effective, reliable assessment.
Tracking evaluation results over time to measure real progress from proof-of-concept to production.
About the speaker
Viktoria Semaan:
Viktoria Semaan is a Principal Technical Evangelist and AI Engineer with over 15 years of experience across cloud technologies, engineering, and management consulting. A recognized AI/ML Top Voice on LinkedIn and one of the leading global cloud influencers, Viktoria is known for turning cutting-edge AI advancements into practical tools and business value. She currently helps developers and enterprises adopt next-generation AI services, leading hands-on initiatives in multi-agent systems, retrieval-augmented generation (RAG), and modern AI toolchains. Her work bridges technical depth with strategic vision, accelerating how teams build and scale with AI. Viktoria holds an MBA from UCLA Anderson and completed an entrepreneurship program at HEC Paris. She is a frequent keynote speaker at major developer conferences worldwide, where she shares actionable strategies on applied AI, developer experience, and innovation at scale. With a following of over 630,000 tech professionals, she also actively mentors the next generation of builders, championing inclusive growth and continuous learning in the AI space.
About
TestMu Conf
Testμ (TestMu) is the world’s largest virtual conference on agentic engineering and quality, built by the community, for the community. As AI reshapes how we build, test, and ship software, Testμ Conf is where you connect, grow, and lead: agentic workflows, autonomous quality, battle-tested AI playbooks, hands-on workshops, and the engineering culture driving it all.
More Sessions
Join the builders, testers, and innovators shaping the next generation of web experiences.
Testμ Conf 2026 is where they meet.
