AI Infrastructure Engineer

Utilidata

2d • $170,000 - $210,000 • Remote

About The Position

Utilidata is a fast-growing NVIDIA-backed edge AI company enabling greater visibility and control of power utilization in energy-intensive infrastructure, like the electric grid and data centers. Karman, the company’s distributed AI platform powered by a custom NVIDIA module, is transforming the way utility companies operate the grid edge and will enable data centers to unlock more compute for the same provisioned power.

The AI Infrastructure Engineer is responsible for designing, building, and owning the end-to-end infrastructure that serves Utilidata's AI and ML models across edge deployments, cloud environments, and data center integrations. They are also responsible for designing, building, and owning the integration of power data with AI inference software. This is Utilidata's first dedicated role of this kind, and will serve as the foundational function for how the company deploys and operates AI capabilities in production. The role requires deep technical expertise in ML model serving, distributed systems, and GPU infrastructure, with a strong emphasis on reliability, performance, and scalability. This position works cross-functionally with product, engineering, and data science teams and is open to fully remote candidates, with periodic travel expected for company retreats and key on-site engagements.

Requirements

• 5+ years of software engineering experience with a strong focus on AI infrastructure, backend systems, or distributed systems
• Hands-on experience with AI model serving frameworks (e.g., vLLM, SGLang, Triton, TensorRT, TorchServe, or similar)
• Understanding of container orchestration and cluster management (Kubernetes, Docker)
• Experience deploying and operating infrastructure across both datacenter and on-prem environments
• Strong knowledge of GPU workloads and the tradeoffs that come with them — you understand how inference differs from training, and why it matters
• Proficiency in Python; C++, CUDA, Go, Rust a plus
• Excellent communication skills and comfort working cross-functionally in a lean, fast-moving environment
• Willingness to travel up to 10% of time

Nice To Haves

• Dynamo experience a plus
• Experience with edge AI deployments or constrained compute environments
• Familiarity with infrastructure as code (Terraform, Helm)
• Experience with observability platforms (Datadog, Prometheus, Grafana)
• Background in energy, utilities, or industrial IoT
• Contributions to open-source ML infrastructure projects

Responsibilities

• Lead the design and build of Utilidata's AI inference platform — establishing architecture patterns, deployment standards, and operational practices that will scale with the company
• Own end-to-end model serving infrastructure for Utilidata's AI infrastructure (on-prem and datacenter)
• Build and maintain fault-tolerant, high-performance systems for serving AI models at scale, with a focus on low latency, reliability, and cost efficiency
• Collaborate closely with algorithms engineers to integrate AI inference data and configuration with power optimization algorithms
• Optimize GPU utilization and inference performance across our hardware fleet, including NVIDIA accelerators central to Utilidata's edge AI platform
• Establish MLOps best practices including CI/CD pipelines for model deployment, monitoring, and rollback across environments
• Contribute to infrastructure roadmap decisions, including build vs. buy tradeoffs, tooling selection, and platform evolution as the team grows

Benefits

• Creating a diverse and inclusive workplace that is welcoming, supportive, affirming and respectful
• Empowering employees to solve problems and work together to make a difference
• Providing mentorship and growth opportunities as part of a collaborative team
• A flexible work environment with flexible paid time off
• Competitive compensation and benefits, including health, dental, vision, and employer-match 401k

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed
• Number of Employees: 1-10 employees