Software Development Manager, Alexa Sensitive Content Intelligence (ASCI)

About the role

The Alexa Sensitive Content Intelligence (ASCI) team builds the Responsible AI platform that safeguards Alexa+ experiences worldwide. As a Software Development Manager you will lead a team that delivers production‑grade ML inference infrastructure and content‑safety services for both cloud‑based and on‑device moderation.

Key responsibilities

• Lead and grow a high‑performing engineering team delivering ML inference and content‑safety services for Alexa+.
• Own inference optimization strategies for GPU/CPU in the cloud and model compression/distillation for on‑device deployment.
• Design and operate a 1‑click continuous model deployment pipeline with zero‑downtime rollouts, automated validation, and rollback across cloud and edge targets.
• Architect scalable real‑time and batch serving systems handling multi‑modal content (text, image, video, LLM invocations) at global scale.
• Drive on‑device moderation capabilities, optimizing latency, memory, and power while maintaining accuracy.
• Ensure operational excellence: 99.95%+ availability, low latency, cost efficiency, and multi‑region reliability.
• Partner with applied scientists on model trade‑offs and with platform teams on traffic migration, capacity planning, and device integration.
• Mentor and develop senior engineers with a focus on emerging ML hosting and infrastructure optimisation.

Required profile

• Proven experience leading engineering teams that build and operate ML inference services.
• Strong track record of making architecture decisions for cloud and edge environments.
• Excellent communication skills with senior management and cross‑functional partners.
• Ability to mentor engineers and foster a culture of continuous learning.

Required skills

• Machine Learning inference infrastructure
• GPU/CPU serving optimization
• Model compression and distillation
• Continuous deployment pipelines with zero‑downtime rollouts
• Scalable real‑time and batch serving systems
• Multi‑modal content processing (text, image, video, LLM)
• On‑device deployment constraints (latency, memory, power)
• Operational metrics: availability, latency, cost, reliability