Develop and maintain backend services for AI/ML systems, integrating and optimizing LLM inference, REST APIs, and MLOps pipelines in a hybrid role.
- Build and maintain production services
- Collaborate on system architecture
- Contribute to MLOps best practices
- Design REST APIs
- Implement CI/CD pipelines
- Integrate and serve LLMs
- Monitor and optimize API performance
- Optimize model inference cost
- Package models for deployment
- Write unit tests and review code
Perks/Benefits:
- Conferences
- Flexible hours
- GPU access
- Hybrid work
- Mentorship
- Training