📍 San Francisco — Onsite I'm hiring an Evaluation Researcher for a well-funded frontier AI startup building at the intersection of multimodal AI, real-time voice systems and intelligent agents. The team is developing next-generation AI companions capable of understanding live environments, holding natural conversations, managing interruptions and interacting with users in real time. They're looking for someone to help define, measure and improve what makes these AI systems genuinely intelligent, reliable and engaging. The Role You'll work on the research and development of evaluation frameworks for real-time, multimodal AI systems, designing benchmarks and testing methodologies that measure model performance across speech, reasoning, interaction and conversational behaviour. Looking for: • Strong ML research and engineering fundamentals. • Experience with LLM evaluations, benchmarking or model assessment. • Strong Python and deep learning experience. • Familiarity with multimodal models, speech AI or conversational agents. • Ability to design experiments, analyse model behaviour and translate findings into improvements. Backed by leading venture capital investors and prominent startup accelerators, this is an opportunity to join an early-stage research team and help shape how next-generation AI systems are evaluated. If you're interested in working at the forefront of LLM evaluations, multimodal AI and real-time intelligent systems, apply now to learn more about this opportunity.