Responsibilities
- Develop and maintain robust evaluation systems to track model accuracy, performance shifts, and operational costs in live environments.
- Design and implement scalable backend services and APIs in Python using FastAPI to support large language models under heavy workloads.
- Create and optimize Retrieval-Augmented Generation (RAG) pipelines, including selection of vector databases and tuning of embedding techniques for speed and precision.
- Implement observability tools and safety controls to monitor model behavior, detect data drift, and prevent harmful outputs such as hallucinations or biased content.
- Build secure interfaces that enable AI agents to interact reliably with enterprise platforms, customer relationship systems, and older database infrastructures.
- Lead peer code reviews, mentor engineers, and promote ongoing technical growth within the development team.
- Work closely with infrastructure teams to plan scalable deployment approaches that adapt to variable traffic demands.
- Own the full architectural design of AI applications on cloud environments, with a focus on Google Cloud Platform, ensuring resilience, security, and efficient resource use.
Benefits
- Medical plan with no out-of-pocket premium
- Employer-funded contributions to Health Savings Account
- Support for fertility treatments and family-building
- Fully employer-paid parental leave
- Monthly allowance for personal lifestyle expenses
- Additional benefits available
Work Arrangement
Hybrid
