Summary by AIEngineer.careers
Forward Deployed Engineer - AI Inference Systems Research is a Forward Deployed AI Engineer role (full-time). with Nutanix. in VANCOUVER, CA. Compensation shown: $88K–$132K (est.). Imported listing (source: mydeltabc.ca). Apply on the employer's site (mydeltabc.ca).
Imported listing (source: mydeltabc.ca) · Apply on mydeltabc.ca
How our listings work
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from mydeltabc.ca
Entry-level Forward Deployed Engineer on Nutanix's AI Solutions Engineering team in Vancouver, bridging product engineering, systems research, and enterprise deployments. You will deploy end-to-end AI infrastructure on the Nutanix Cloud Platform, triage complex distributed systems failures, and build automation to reduce deployment friction. Structured time is dedicated to inference research, benchmarking open-source serving engines and optimizing GPU utilization.
Responsibilities
- Deploy, configure, and validate Nutanix Enterprise AI workloads across hybrid multi-cloud and on-premises environments
- Perform root-cause analysis on GPU orchestration, container networking, storage I/O, and model runtime failures
- Debug across Linux internals, hypervisors, and Kubernetes clusters to resolve critical customer incidents
- Build automation scripts, CLI tools, Helm charts, and reference architectures for deployment pipelines
- Benchmark modern inference frameworks such as vLLM, TensorRT-LLM, TGI, and Triton Inference Server
- Profile inference pipelines to optimize latency, throughput, TTFT, and inter-token latency on NVIDIA and AMD accelerators
- Prototype speculative decoding, KV cache management, continuous batching, and quantization techniques
Requirements
- PhD or Master's degree in Computer Science, Computer Engineering, AI, or related quantitative field with focus on AI/ML systems, distributed systems, OS, or computer architecture
- Strong proficiency in Python and C++ or Go, emphasizing systems programming, concurrency, and API development
- Deep knowledge of Linux, performance profiling, Docker, and Kubernetes
- Hands-on experience deploying, serving, or profiling LLMs and diffusion models with PyTorch and serving frameworks like vLLM, Hugging Face TGI, or Triton
- Ability to communicate complex distributed systems failures clearly to customers and engineering teams
Nice to Have
- Internship, research fellowship, or co-op in forward deployed engineering, SRE, infrastructure engineering, or ML platform development
- Experience with CUDA, NVIDIA Nsight Systems, Triton kernels, or ROCm
- Familiarity with enterprise storage (POSIX, S3/Object Store, NVMe-oF) and virtualization (KVM, AHV)
- Contributions to open-source inference runtimes, distributed ML libraries, or Kubernetes operators
Benefits
rrsp matchingmental health supportParental leaveEquity / stock optionsrsuemployee stock purchase planpaid time offhybrid work
Tech Stack
AWQC++CUDADiffusion ModelsDockerFP8GoGPTQHelmKubernetesLinuxLLMsNVIDIA Nsight SystemsPythonPyTorchROCmTensorRT-LLMTGITriton Inference ServervLLM