Loading...
Mid LevelFull-timePythonRustKubernetesPyTorchGoAI
Salary Range
$102,000 - $138,000 /year
This salary is estimated based on similar roles. The actual salary may vary.
About the Role
Fluidstack is seeking an Inference Platform Engineer to join our team. This hands-on role focuses on building and maintaining the infrastructure that powers inference for frontier AI models, working with top AI labs and enterprises.
Key Responsibilities
- →Own inference deployments end-to-end, from configuration to production maintenance
- →Drive improvements in throughput, TTFT, and cost-per-token across diverse model families
- →Build and operate KV cache and scheduling infrastructure for maximum utilization
- →Implement and validate disaggregated prefill/decode pipelines and Kubernetes orchestration
- →Profile and resolve bottlenecks at compute, memory, and communication layers
- →Partner with customers to translate requirements into deployment configurations
- →Contribute to inference platform architecture and roadmap
- →Participate in on-call rotation for production deployments
Requirements
- ✓5+ years of professional software engineering experience
- ✓Strong programming skills in Python and/or Go
- ✓Production experience with LLM serving frameworks
- ✓Working knowledge of PyTorch or JAX
- ✓Experience deploying GPU workloads on Kubernetes at scale
- ✓Solid understanding of GPU memory hierarchies and parallelism strategies
- ✓Ability to communicate technical tradeoffs clearly
- ✓Excellent written and verbal communication skills in English
Benefits
- ★Competitive total compensation package (salary + equity)
- ★Retirement or pension plan
- ★Health, dental, and vision insurance
- ★Generous PTO policy
Free to sign up. Takes 30 seconds.
