Responsibilities
- Create scalable components of the ML platform supporting agentic architectures, such as retrieval pipelines, indexing methods, and model integration layers.
- Deploy and manage retrieval-augmented generation (RAG) applications, covering data acquisition, embedding creation, and retrieval behavior at inference time.
- Build standardized evaluation systems for large language models and agent-driven capabilities, incorporating offline benchmarks, curated datasets, and ongoing performance tracking.
- Develop reusable tools, abstractions, and design patterns to accelerate the development of ML- and LLM-enabled features across teams.
- Work closely with backend engineering to deploy ML functionalities with high reliability, monitoring, and performance efficiency.
- Build and test proof-of-concept ML solutions to assess technical viability prior to full-scale implementation.
- Ensure data integrity and security throughout ML processing and retrieval workflows.
- Coordinate with product, design, and engineering stakeholders to align machine learning system design with user needs and product objectives.
- Support ongoing enhancements to the Nova agent framework, particularly workflows developed using Mastra and TypeScript.
Work Arrangement
Remote (Worldwide) — San Francisco, New York, Denver, London, Lisbon, remote worldwide
Other
- Flexible paid time off
- Balance Days (additional paid holidays)
- Paid sabbatical after tenure
- Monthly wellness stipend
- Monthly professional growth allowance
- Pre-tax commuter benefits
- Complete laptop workstation provided
