Senior Research Engineer: Real-Time Model Inference

If you are a Research Engineer with expertise in model optimization and integration into production environments, and a passion for applying state-of-the-art AI innovations to make conversations more valuable, look no further! As a Research Engineer on our Platform team, you'll advance the frontier of AI by maximizing efficiency and performance to achieve feats previously thought impossible. You’ll do so by optimizing and deploying machine learning models for real-time applications. Join us alongside a cohort of industry-leading scientists, ML engineers, and production engineers as we grow Otter’s AI-powered collaboration platform that’s transcribed over 1B meetings. Together, we strive to elevate the value of conversations through innovative solutions. Your Impact Model optimization: Collaborate with machine learning researchers to understand model architectures and algorithms. Implement optimization techniques to enhance machine learning models' efficiency and inference speed on production Deployment and Integration: Work closely with product engineers to integrate machine learning models into production systems in a scalable way Optimize models for real-time inference, ensuring low latency and high-throughput Set up monitoring systems to track model performance in real time. Ensure models can scale horizontally to handle the increased load. Implement strategies for resource-efficient inference, considering factors such as memory usage and CPU/GPU utilization. Collaborate with cross-functional teams to understand requirements and constraints. Provide technical expertise on inference-related matters during the model development lifecycle. Document the deployment and optimization processes for machine learning models. We're looking for someone who 5+ years of professional industry experience Masters or Ph.D. degree in computer science, machine learning, speech/language processing or related field Experience in PyTorch Proficiency in Python Experience in C++ Basic knowledge of CUDA Strong understanding of machine learning models, algorithms, and deployment strategies Experience with model optimization techniques and performance profiling Familiarity with docker and Kubernetes Knowledge of AWS Experience with monitoring tools About Otter.ai We are in the business of shaping the future of work. Our mission is to make conversations more valuable. With over 1B meetings transcribed, Otter.ai is the world’s leading tool for meeting transcription, summarization, and collaboration. Using artificial intelligence, Otter generates real-time automated meeting notes, summaries, and other insights from in-person and virtual meetings - turning meetings into accessible, collaborative, and actionable data that can be shared across teams and organizations. The company is backed by early investors in Google, DeepMind, Zoom, and Tesla. #J-18808-Ljbffr Otter.ai