Staff AI Platform Engineer, Developer Experience

Analog Devices•Wilmington, MA

1d•Hybrid

About The Position

This role is within the global Developer Experience (DevEx) team, specifically the Model Developer Experience (MDX) sub-team – whose mission is to deliver world-class infrastructure and platforms that enable AI builders across ADI to move faster, with confidence, and at scale. You will join a high-performance, mission-driven interdisciplinary team that spans data science, software engineering, platform architecture, cloud infrastructure, and security expertise. We believe in a culture founded on trust, mutual respect, growth mindsets, and an obsession for building extraordinary products with extraordinary people. As a Staff/ Senior AI Platform Engineer (individual contributor), you will bring deep technical expertise in building scalable AI infrastructure across diverse deployment environments, and the ability to design elegant solutions that absorb operational complexity on behalf of AI builders across the organization. You will work embedded with data science and ML engineering teams to understand their infrastructure needs at the cutting edge, then translate those learnings into reusable, org-wide architectural patterns and platforms. You'll design and implement critical infrastructure capabilities that span on-prem, hybrid, and cloud environments—from model serving and orchestration, to compute optimization, cost efficiency, and governance. You will work at the intersection of research, technical architecture, and developer enablement—translating research and product goals into infrastructure systems that reduce friction and accelerate innovation.

Requirements

Deep expertise in designing and operating AI workloads across multiple deployment paradigms (on-premises, hybrid, cloud-native).
Proven ability to work embedded with technical teams, understand complex requirements, and translate them into scalable architectural solutions.
Strong experience with Kubernetes, container orchestration, and distributed compute frameworks (Ray, Spark, or equivalent) at production scale.
Expert-level Infrastructure-as-Code proficiency (Terraform, CDK, or equivalent) with demonstrated ability to build reusable, multi-team infrastructure templates.
Deep knowledge of GPU/accelerator resource management, including scheduling, optimization, and cost tracking across heterogeneous hardware.
Experience designing model serving infrastructure and inference optimization pipelines for production AI workloads.
Demonstrated ability to solve complex infrastructure problems through systematic analysis and creative engineering.
Strong communication skills and ability to translate technical concepts for both engineering and non-technical audiences.
Familiarity with risk-tiered compliance models where control intensity scales with assessed risk level.
Strong cross-functional collaboration skills — ability to work across Legal, Security, Privacy, and Engineering to align on governance workflows without creating organizational friction.
Mentoring orientation with demonstrated success upskilling scientists on infrastructure and platform topics.

Nice To Haves

Experience building or scaling AI infrastructure for robotics, autonomous systems, or industrial perception applications.
Familiarity with ROS/ROS2 ecosystems and the infrastructure challenges of deploying ML models in robotic systems.
Background in edge AI deployment, including optimization for low-latency inference on resource-constrained devices.
Experience designing ML infrastructure that supports rapid iteration and few-shot adaptation in physical systems.
Knowledge of heterogeneous compute architectures combining CPUs, GPUs, and specialized processors (NPUs, FPGAs, etc.).
Experience with real-time operating systems or hard real-time constraints in distributed systems.
Understanding of manufacturing, autonomous vehicle, or healthcare domains and their infrastructure requirements for AI applications.

Responsibilities

Partner directly with AI builder teams (data scientists, ML engineers, researchers) as an embedded technical advisor, understanding their infrastructure bottlenecks and platform needs at the point of creation.
Translate specific team engagements into generalizable patterns, standards, and architectural guidance that can be adopted across the organization.
Drive initiatives that reduce friction in the AI development lifecycle—from experimentation through production—by removing operational and technical barriers for builders.
Design and advocate for developer-friendly abstractions and APIs that hide infrastructure complexity while maintaining flexibility for advanced use cases.
Collaborate with cross-functional stakeholders to define what "excellent developer experience" means for AI developers.
Shepherd ML/AI projects through ADI's AI Supply Chain ensuring governance gates are met at each transition.
Facilitate cross-functional approval workflows spanning Legal, Security, Trade Compliance, Data Privacy, and Responsible AI stakeholders for high-risk model promotions.
Design and optimize AI infrastructure strategies that span heterogeneous environments—on-prem GPU clusters, hybrid cloud-edge deployments, and cloud-native architectures—ensuring seamless developer experience across all.
Architect compute orchestration and scheduling solutions (Kubernetes, Ray, or equivalent) that efficiently allocate resources across multiple environments and workload types.
Own infrastructure for model serving, inference optimization, and real-time inference pipelines supporting low-latency, edge-deployed AI models.
Define and implement cost optimization strategies across cloud and on-prem resources, including resource allocation, auto-scaling policies, and workload consolidation.
Build reusable Infrastructure-as-Code frameworks and tooling that other teams can adopt to provision and manage AI workloads consistently across environments.
Establish observability and monitoring strategies for AI infrastructure, including resource utilization, cost tracking, and performance metrics that enable proactive problem-solving.
Drive security and compliance standards for AI infrastructure, ensuring data residency, access control, and auditability across deployment environments.
Mentor engineers on infrastructure best practices, distributed systems concepts, and optimization techniques that improve platform reliability and developer productivity.