Machine Learning Engineer - Inference and Production
📍
Mountain View, CA
🧪
Entry level
About The Company
At Resemble AI, we are at the forefront of Generative Voice AI, transforming how content is created and consumed across various industries. Our cutting-edge text-to-speech generator, coupled with real-time APIs, enables the creation of immersive voice-centric experiences. Our technology is trusted by creatives and corporations alike for applications in advertising, gaming, virtual assistance, and call centers, delivering flexibility and realism in speech like never before.
About The Role
As a Machine Learning Engineer focusing on inference and serving models in production, you will be instrumental in operationalizing and optimizing our AI models for live environments. This role places you at the heart of our production team, where you will ensure the seamless deployment and scalability of our voice AI technologies.
What You'll Do
At Resemble AI, we are at the forefront of Generative Voice AI, transforming how content is created and consumed across various industries. Our cutting-edge text-to-speech generator, coupled with real-time APIs, enables the creation of immersive voice-centric experiences. Our technology is trusted by creatives and corporations alike for applications in advertising, gaming, virtual assistance, and call centers, delivering flexibility and realism in speech like never before.
About The Role
As a Machine Learning Engineer focusing on inference and serving models in production, you will be instrumental in operationalizing and optimizing our AI models for live environments. This role places you at the heart of our production team, where you will ensure the seamless deployment and scalability of our voice AI technologies.
What You'll Do
- Implement, monitor, and maintain machine learning models in production environments to ensure high availability and low latency.
- Collaborate with data scientists and developers to optimize model performance, including resource management and cost efficiency.
- Design and develop robust systems for real-time inference and batch processing of voice data.
- Manage the lifecycle of models from deployment to updates and scaling, ensuring smooth transitions and minimal downtime.
- Develop tools and frameworks to automate model training, testing, validation, and deployment processes.
- Continuously evaluate and incorporate state-of-the-art ML deployment practices and technologies into the infrastructure.
- Work closely with product teams to integrate AI capabilities into customer-facing applications.
- Deploy scalable machine learning solutions across multiple platforms and environments.
- Optimize machine learning pipelines for performance and speed.
- Monitor model performance and make adjustments to inference configurations.
- Ensure data privacy and security standards are upheld in deployment processes.
- Provide technical leadership and insights to improve product features and architecture.
- Strong experience in deploying and managing machine learning models in production.
- Proficient with ML deployment tools (e.g., TensorFlow Serving, TorchServe) and cloud platforms (AWS, GCP, Azure).
- Expertise in Python and familiarity with software development best practices.
- Knowledge of containerization and orchestration technologies (Docker, Kubernetes).
- Excellent problem-solving, troubleshooting, and analytical skills.
- Degree in computer science, engineering, or related field with a specialization in machine learning.
- Experience with voice or speech recognition technologies.
- Familiarity with performance tuning and optimization of real-time systems.
- Contributions to open-source projects or active engagement in the ML community.