FriendliAI
Forward Deployed Engineer - AI Inference
San Francisco · Hybrid · Full-time · Posted Oct 7, 2026
- Experience
- 3+ years in cloud infrastructure, DevOps, or reliability engineering.
- Education
- Bachelor’s or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent.
About the job
Deploys and operates production-grade generative and agentic AI inference workloads on FriendliAI infrastructure, working directly with customers and their engineering teams.
What you'll do
- Design and implement deployment architectures for LLM and multimodal inference; manage containerized workloads on Kubernetes.
- Diagnose production issues and integrate infrastructure into customer CI/CD workflows; develop scripts, Helm charts, and Terraform modules.
- Share customer insights to improve reliability, observability, and scaling, and lead technical workshops or sessions.
What they ask for
- Proficiency with Kubernetes, Docker, Terraform, and Helm.
- Strong foundation in distributed systems, networking, and performance tuning.
- Experience with GPU-based computing and generative AI model serving workloads.
- Experience operating workloads on AWS, GCP, or OCI.
Nice to have
- Experience deploying large models on GPUs or clusters; familiarity with inference frameworks such as Triton, vLLM, TensorRT, or DeepSpeed-Inference.
- Familiarity with observability stacks or networking security and compliance frameworks; experience with on-premises or hybrid-cloud deployments.
Tools
Kubernetes, Docker, Terraform, Helm, AWS, GCP, OCI, Triton
AI focus
Deploying, scaling, and operating generative and agentic AI inference workloads, including LLM and multimodal model serving.
Model-written summary · the original posting is authoritative