Senior ML Ops & Customer Support Engineer – AI Inference

About Us

Qualcomm is enabling a world where everyone and everything can be intelligently connected. You interact with products and technologies made possible by Qualcomm every day, including intelligent edge devices, next‑generation computing platforms, and advanced AI solutions. Qualcomm’s leadership in AI, high‑performance compute, and connectivity is driving innovation across cloud, edge, and data centre environments, delivering scalable, power‑efficient platforms that power the next generation of intelligent infrastructure.

Qualcomm is seeking a Machine Learning Operations & Customer Support Engineer within the Customer Engineering team to support strategic customers deploying AI inference workloads on advanced Qualcomm AI inference accelerators. These accelerators utilize Qualcomm's expertise in hardware‑accelerated AI to deliver high‑performance, energy‑efficient generative AI and computer vision inference solutions for modern data centres.

This is a customer‑facing, production‑critical role focused on ensuring maximum system uptime, reliability, and performance, while resolving customer support cases within defined SLAs/KPIs. The role requires deep expertise across ML inference pipelines, systems troubleshooting, and data centre operations, working closely with customers, internal engineering, and product teams.

The ideal candidate will bring a strong foundation in ML model deployment, systems engineering, rack‑scale management software, Dev Ops/MLOps automation, and cross‑functional collaboration.

• Act as the primary technical escalation point for customer issues related to AI inference workloads.
• Own end‑to‑end case management, ensuring resolution within agreed SLAs and KPIs.
• Drive incident response, triage, and root cause analysis (RCA).
• Provide timely and transparent communication to customers on issue status and resolution.
• Maintain high levels of customer satisfaction and service reliability.

• Ensure high availability and uptime of customer AI deployments (rack‑scale systems).
• Monitor system health, performance metrics, and workload behaviour.
• Implement and manage failover, redundancy, and resiliency mechanisms.
• Proactively identify risks and implement preventative actions.

• Support deployment, optimisation, and troubleshooting of ML inference pipelines.
• Debug issues across model, runtime, system, and hardware layers.
• Analyse model performance (latency, throughput, accuracy trade‑offs) in production.
• Support frameworks such as PyTorch, Tensor Flow, ONNX, and model conversion flows.
• Assist in model optimisation techniques (quantisation, batching, compilation, runtime tuning).

• Support bare‑metal and virtualised environments for AI workloads.
• Troubleshoot issues across Linux OS, drivers, firmware, and networking stack.
• Support deployment and maintenance using Infrastructure as Code (IaC) and automation tools.
• Work with DCIM tools and monitoring systems for infrastructure visibility.
• Coordinate with hardware vendors for accelerator, server, and networking issues.

• Implement and manage monitoring systems (logs, metrics, traces).
• Build dashboards for uptime, SLA adherence, performance, and utilisation.
• Automate repetitive operational tasks using scripts and workflows.
• Establish and enforce runbooks and standard operating procedures (SOPs).

• Work closely with Customer Engineering, Product, Engineering, and Support teams.
• Provide structured feedback to engineering for product improvements and defect resolution.
• Support customer onboarding, deployment readiness, and operational handover.
• Participate in customer reviews, escalations, and technical deep dives.

• Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or related field.
• 10–15+ years of experience in ML operations, systems engineering, or customer support engineering.
• Proven experience in customer‑facing technical roles with SLA‑driven support models.
• Strong experience with AI/ML inference…