Member of Technical Staff, Inference & Serving
InceptionVisit Inception website
AI research and product company building diffusion-based language models for production applications.
Palo Alto, United States
Funding history
About Inception
Inception develops and deploys the Mercury family of diffusion LLMs, which generate and refine output in parallel to target lower-latency, lower-cost production AI workloads.
Skills
About the Role
You will build low-latency model serving systems and distributed inference infrastructure. You will manage traffic, autoscaling, versioning, deployments, and observability, while converting model advances into production serving improvements.
Requirements
- Machine learning serving
- SGLang
- vLLM
- Triton Inference Server
- TensorRT-LLM
- PyTorch
- TensorFlow
- High-performance computing
- GPU programming
- CUDA
- Docker
- Kubernetes
- CI/CD
- Performance optimization
- Profiling
Responsibilities
- Build and optimize low-latency model serving systems
- Extend distributed inference and serving orchestration frameworks
- Manage load balancing autoscaling and traffic routing
- Build model versioning canary deployment and zero-downtime rollout systems
- Develop monitoring alerting and observability tooling
- Translate model advances into production serving improvements
Benefits
- Equity
- Flexible vacation and paid time off
- Health insurance
- Dental insurance
- Vision insurance
- 401k match
- Catered meals
- Commuter subsidies