10a Labs is looking to productionize ML systems for real-time use, requiring the development of APIs, orchestration logic, and internal tools to support moderation workflows, annotation interfaces, and monitoring dashboards. The goal is to deliver high-reliability systems for abuse detection, threat classification, and review queues, transforming complex models into accessible, performant APIs.
Requirements
- Has 3–8 years of backend engineering experience (Python preferred).
- Has designed and deployed production APIs in high-reliability environments.
- Understands how to integrate ML models, inference systems, or vector search pipelines into backend applications.
- Has experience with modern infrastructure stacks (Docker, Terraform, CI/CD, GCP or AWS).
- Has strong knowledge of software development lifecycles and best practices.
- Strong proficiency with Python or another modern backend language.
- Experience designing APIs (REST, gRPC, FastAPI, Flask, etc.).
Responsibilities
- Design and build secure, high-performance APIs for inference, review workflows, and system orchestration.
- Develop internal tools to manage policy configs, annotations, and review queues.
- Integrate ML classifiers and LLMs into backend systems for streaming or batch inference.
- Build and maintain system monitoring for latency, errors, throughput, and system performance.
- Implement CI/CD pipelines and ensure the reliability and scalability of backend services.
- Design and deploy a stable, documented API for real-time model inference.
- Integrate at least one ML model into a production system with sub-200ms latency.
Other
- 3–8 Years of Industry Experience
- Remote
- High-Impact
- Moves quickly in ambiguous environments and takes ownership end to end.
- Clear communicator who can write well and explain system decisions to technical and non-technical teammates.
