Forward Deployed Engineer - AI Inference

Hungry, Humble, Honest, with Heart.

The Opportunity

When people talk about generative AI and other ML-powered solutions in today's conversation, they often refer to generative pre-trained transformers like ChatGPT that can respond to queries from a position of deep learning. A GPT-in-a-box solution removes the burden of building or implementing these AI solutions yourself. It also makes overcoming the complexity, inefficiency, and security challenges of generative AI and AI/ML applications easy. Nutanix simplifies your learning curve on AI-ready infrastructure with Nutanix Cloud Platform for AI (GPT-in-a-Box). This high-performant Machine Learning full-stack cloud platform helps you optimise IT costs with a software-defined cloud operating model. Harness AI-ready capabilities right out of the box, simplified to build, fine-tune, and run models, including GPTs and LLMs, while you continue to use existing teams and skills.

Join the Nutanix AI team, responsible for the magic behind the scenes.

About the Team:

The Nutanix AI Solutions Engineering and Forward Deployed Engineering (FDE) team operates at the critical intersection of applied research, systems engineering, and customer success. Our charter spans three core pillars:

• Field Engineering & Production Deployment: Delivering hands-on technical onboarding, architecture integration, and rapid triage for enterprise customers deploying the Nutanix AI (NAI) platform.
• Solutions Engineering: Abstracting common edge cases and deployment challenges across diverse customer environments into resilient, reusable frameworks, automated blueprints, and core product enhancements.
• Inference Research: Investigating, benchmarking, and integrating cutting-edge model serving techniques, hardware acceleration runtimes, and quantization algorithms directly into the NAI stack.

Role Overview
As an entry-level Forward Deployed Engineer based out of our Vancouver office, you will bridge the gap between Nutanix AI product engineering, cutting-edge systems research, and enterprise production environments. You will deploy end-to-end AI infrastructure on the Nutanix Cloud Platform, diagnose complex distributed systems failures, and design programmatic solutions that prevent recurring deployment friction. Additionally, you will dedicate structured time to inference research—evaluating emerging open-source inference engines, optimizing GPU utilization, and benchmarking model serving performance.

You will report to a seasoned Technical Manager who will provide mentorship and guidance as you navigate through your responsibilities. The work setup at Nutanix AI is a hybrid model, offering a blend of in-office collaboration and remote work flexibility. As a new hire, you will be expected to be in the office for 3 days a week, ensuring that you have the opportunity to engage with your team and foster strong working relationships.

Your Role: 

• Customer Deployments & Issue Triage
  • Partner directly with enterprise customers to deploy, configure, and validate Nutanix Enterprise AI workloads across hybrid multi-cloud and on-premises environments.
    
  • Perform root-cause analysis on real-time failures spanning GPU orchestration, container networking, storage I/O bottlenecks, and model runtime crashes.
    
  • Serve as the frontline technical authority, driving critical customer incidents to resolution through hands-on debugging across Linux internals, hypervisors, and Kubernetes clusters.
• Solutions Engineering & Tooling
  • Identify recurring patterns in customer configurations, support tickets, and performance regressions.
  • Develop production-grade automation scripts, CLI tools, Helm charts, and reference architectures to streamline deployment pipelines across heterogeneous environments.
  • Feed operational insights, reproducible test beds, and code patches back to the core NAI product engineering teams.
• Inference Systems Research & Optimization
  • Experiment with, evaluate, and benchmark modern inference frameworks (e.g., vLLM, TensorRT-LLM, TGI, Triton Inference Server).
  • Profile model inference pipelines to optimize latency, throughput, time-to-first-token (TTFT), and inter-token latency (ITL) on modern accelerator architectures (NVIDIA, AMD).
  • Prototype applied techniques such as speculative decoding, KV cache management strategies, continuous batching, and quantization (AWQ, FP8, GPTQ) for platform integration.
    

What You Will Bring

• Education: Ph.D. in Computer Science, Computer Engineering, Artificial Intelligence, or a related quantitative field with an academic or thesis focus on AI/ML systems, distributed systems, operating systems, or computer architecture.

• Programming: Strong proficiency in Python and C++ or Go, with an emphasis on systems programming, concurrency, and API development.

• Systems & Infrastructure: Deep theoretical and practical knowledge of Linux operating systems, systems performance profiling, containerization (Docker), and container orchestration (Kubernetes).

• AI/ML Runtimes: Hands-on experience deploying, serving, or profiling Large Language Models (LLMs) and diffusion models using PyTorch and open-source serving frameworks (vLLM, Hugging Face TGI, Triton).

• Communication: Ability to distill complex distributed systems failures into clear technical action plans for both customer stakeholders and internal engineering teams.
  Preferred Qualifications

• Prior internship, research fellowship, or co-op experience in forward deployed engineering, site reliability, infrastructure engineering, or ML platform development.

• Direct experience with hardware-aware optimization tools, such as CUDA, NVIDIA Nsight Systems, Triton kernels, or ROCm.

• Familiarity with enterprise storage concepts (POSIX, S3/Object Store, NVMe-oF) and virtualization technologies (KVM, AHV).

• Contributions to open-source inference runtimes, distributed ML libraries, or Kubernetes operators.

Note: Nutanix does not assist with applications for work permits or permanent residence, including provincial nomination.
 
Pay Transparency -Role Location The pay range for this position at commencement of employment is expected to be between CAD $132,000 and CAD $198,000 per annual.
However, base pay offered may vary depending on multiple individualized factors, including market location, job-related knowledge, skills, and experience. The total compensation package for this position may also include other elements, including a sign-on bonus, restricted stock units, and discretionary awards in addition to a full range of medical, financial and/or other benefits (including 401(k) eligibility and various paid time off benefits, such as vacation, sick time, and parental leave), dependent on the position offered. Details of participation in these benefit plans will be provided if an employee receives an offer of employment.
 
If hired, employee will be in an “at-will position” and the Company reserves the right to modify base salary (as well as any other discretionary payment or compensation program) at any time, including for reasons related to individual performance, Company or individual department/team performance, and market factors. Our application deadline is 40 days from the date of posting. In good faith, the posting may be removed prior to this date if the position is filled or extended in good faith.

--