PADOInfrastructure & platform
AI role: posting shows model training or post-training, model inference and serving. How we decide
PM, Compute Platform
Summary
Role at PADO, Product team. RoleRadar classifies it as infrastructure & platform. Listed location: Washington, DC. The posting asks for 4–10 years of experience. Skills mentioned include Triton, vLLM / TensorRT, Inference optimization, A/B testing, Kubernetes and GPU clusters & HPC.
Generated by RoleRadar from facts in the posting. We don't reproduce the job description; read it in full on PADO's job page.
Key facts
- Salary
- Not published by the employer
- Location
- Washington, DC
- Workplace
- Not stated in the posting
- Countries
- United States
Inferred by RoleRadar from the listed locations.
- Experience
- 4–10 years asked for
- PhD
- Not mentioned
- Visa sponsorship
- Not stated in the posting
- Team
- Product
Skills mentioned
- Triton
- vLLM / TensorRT
- Machine learning
- Inference optimization
- A/B testing
- Kubernetes
- GPU clusters & HPC
- Observability
Links go to free learning resources, official documentation where it exists. No affiliate links.