Senior Software Engineer - Inference /AI

Role Overview

At Nutanix, you will help shape the next generation of enterprise AI platforms, working at the intersection of large-scale distributed systems and machine learning infrastructure. This is an opportunity to solve complex technical challenges, influence the direction of key AI technologies, and build systems that power AI workloads at enterprise scale.

Responsibilities

• Architect, design, and develop horizontally scalable, containerized, fault-tolerant services on Kubernetes for enterprise AI and LLM workloads.
• Build and operate high-performance inference and platform services that deliver low-latency, high-throughput experiences for Generative AI and Agentic AI applications.
• Design and optimize critical system components across the stack, including distributed systems, storage, networking, and low-level infrastructure layers.
• Develop and enhance multi-tenant platform services supporting on-premises, hybrid, and cloud-based AI deployments.
• Design and implement scalable observability architectures using technologies such as Prometheus, Grafana, Datadog, OpenTelemetry, and related cloud-native monitoring frameworks.
• Debug complex production issues, perform root-cause analysis, and improve reliability, resiliency, and operational efficiency of platform services.
• Build and maintain CI/CD pipelines and deployment automation to accelerate delivery of production-grade services.
• Design and implement foundational LLM serving capabilities including request routing, rate limiting, token streaming, load balancing, quota management, and usage budgeting.
• Collaborate closely with globally distributed product management, AI, and software engineering teams to deliver high-quality products in a fast-paced environment.
• Contribute to all stages of the product lifecycle, including architecture, design, development, testing, experimentation, performance analysis, deployment, and operations.

Required Qualifications

• 8+ years of experience developing maintainable, modular, resilient, fail-safe, and long-lived software products within a product development organization.
• Strong computer science fundamentals including data structures, algorithms, operating systems, networking, and distributed systems.
• Hands-on experience with Docker, Kubernetes, and cloud-native architectures.
• Production experience developing backend systems using Go, Python, C++, or Rust.
• Experience building, owning, and maintaining CI/CD pipelines and release automation end-to-end.
• Strong understanding of datacenter architecture including compute, storage, networking, and virtualization.
• Experience designing and deploying software across on-premises, cloud, and hybrid environments.
• Demonstrated experience designing and tuning high-performance, performance-sensitive system software.
• Solid understanding of distributed computing, distributed data stores, and large-scale service architectures.
• Experience diagnosing and resolving production performance issues using observability and monitoring platforms such as Prometheus, Grafana, Datadog, Open Telemetry, or similar tools.
• Familiarity with LLM serving concepts including rate limiting, token streaming, request scheduling, load balancing, quota management, and usage budgeting.
• Familiarity with modern LLM concepts including reasoning workflows, tool calling, prompt templates, and agent.
• Experience building multi-tenant services running on virtualized or containerized infrastructure.
• Strong communication, collaboration, and problem-solving skills with the ability to work effectively across globally distributed teams.
• Master's degree in Computer Science or equivalent practical experience.

Bonus Points If You Have Experience With

• Machine learning frameworks such as PyTorch or TensorFlow.
• GPU-based systems and acceleration technologies.
• Modern model-serving platforms such as vLLM, DeepSpeed, Hugging Face TGI, or Triton.
• Retrieval-Augmented Generation (RAG), vector databases, and AI orchestration frameworks.
• Open-source contributions or experience working in large distributed codebases.
• Production AI platforms, LLM APIs, agentic systems, or inference infrastructure.
• Building or scaling production LLM APIs, including streaming via SSE/WebSockets, prompt guardrails, rate limiting, and usage budgeting.

Work Arrangement

The role operates in a hybrid capacity, blending the benefits of remote work with the advantages of in-person collaboration. In locations where our workplace policy applies (i.e. San Jose, Durham, Mexico City, Vancouver, Bangalore, Pune, Hoofddorp, Belgrade, Barcelona, Singapore, Sydney and Tokyo), employees are expected to work onsite a minimum of 3 days per week to foster collaboration, team alignment, and access to in-office resources. Workplace type may vary based on location and team requirements. Please speak with your recruiter for details. Additional team-specific guidance and norms will be provided by your manager.