Research Engineer Post Training Inference
Together AIVisit Together AI website
Together AI operates an AI-native cloud platform for open and custom AI models.
San Francisco, United States
About Together AI
Together AI provides production AI infrastructure spanning inference, accelerated compute, model training and fine-tuning, and secure code sandboxes for AI development.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will develop systems for customizing open-source models and connect post-training to production serving. You will add and optimize inference-engine capabilities for large-scale reinforcement learning workloads, maintain reliable services, and participate in an on-call rotation to support platform availability.
Requirements
- Machine learning service deployment
- Inference engine
- SGLang
- vLLM
- TensorRT-LLM
- LLM fine-tuning
- Python
- Go
- Machine learning
Responsibilities
- Design and build systems for customizing open-source models
- Build integrations between model shaping and inference platforms
- Add inference-engine features for large-scale post-training experiments
- Optimize inference for reinforcement learning workloads
- Maintain stable, robust services
- Participate in an on-call rotation to support platform availability
Benefits
- Startup equity
- Health insurance