AI Engineer & Researcher, Inference
SpeechifyFull Time
Junior (1 to 2 years)
Candidates must possess a Bachelor's, Master's, or Ph.D. degree in Computer Science, Engineering, Mathematics, or a related field, along with at least 1 year of professional work experience in a fast-paced, high-growth environment. A demonstrated proficiency in one or more general-purpose programming languages, preferably Python, used in a production-level setting is required, as is familiarity with AI/ML pipelines and the lifecycle of ML model development and deployment. Strong communication skills for complex technical topics are essential, and experience building or optimizing AI/ML projects is highly valued.
The Applied AI Inference Engineer will partner with customers to architect, build, and deploy high-scale production AI applications on Baseten’s platform, owning the entire customer journey from exploration to production. This includes framing problems, evaluating solutions, deploying services, and monitoring outcomes, working closely with customer engineering teams through sales, implementation, and expansion phases. Responsibilities also involve developing and maintaining software systems and product features, optimizing AI/ML projects, contributing to the technical stack, and functioning as an engineer, project manager, and product manager with a focus on user empathy and execution. Engineers will navigate ambiguity, make sound judgments on tradeoffs, and take pride and ownership in their work.
Platform for deploying and managing ML models
Baseten provides a platform for deploying and managing machine learning (ML) models, aimed at simplifying the process for businesses. Users can select from a library of open-source foundation models and deploy them with just two clicks, making it easier to implement ML solutions. The platform features autoscaling, which adjusts resources based on demand, and comprehensive monitoring tools for tracking performance and troubleshooting. A key differentiator is Baseten's open-source model packaging framework, Truss, which allows users to package and deploy custom models easily. The company operates on a usage-based pricing model, where clients pay only for the time their models are actively deployed, helping them manage costs effectively.