Lead Architect, Autonomous Campaigns Platform

Amazon; New York (NY); On-site; USD 180,000 - 260,000; Full time

Job summary

Amazon is seeking a Senior Software Development Engineer to own the infrastructure, platform, and production systems for autonomous advertising campaigns. You will lead the design, build, and scaling of core services such as tool orchestration and evaluation pipelines.

You will collaborate with applied scientists and engineers to translate prototypes into robust production systems, implement observability and fault tolerance, and ensure low latency and safety guardrails while aligning with

Responsibilities

• Lead engineering strategy and roadmap for Sponsored Products Autonomous Campaigns
• Design and implement scalable architecture to host agent orchestration, tool invocation, state management, and feedback loops
• Build scalable, reusable data and tool registry
• Construct evaluation pipelines (offline and online) to assess agent reasoning quality, performance metrics, safety constraints, and KPI impact
• Integrate and manage tuning pipelines (e.g. hyperparameter tuning, RL fine-tuning, preference optimization), and provide abstraction layers for scientists to plug in models
• Implement observability, logging, metrics, alerting, tracing, and drift detection for agent behaviors and model performance
• Ensure resilience, fault isolation, auto-scaling, batching, caching, resource allocation, concurrency control, and SLA compliance
• Rapidly prototype and evaluate new system designs or algorithmic patterns (e.g. streaming inference, memory caching, chaining of reasoning modules, tool embeddings)
• Collaborate in design reviews, code reviews, system design, and cross-team architecture alignment

Job description

Amazon is seeking a Senior Software Development Engineer to own the infrastructure, platform, and production systems for autonomous advertising campaigns. You will lead the design, build, and scaling of core services such as tool orchestration and evaluation pipelines.

You will collaborate with applied scientists and engineers to translate prototypes into robust production systems, implement observability and fault tolerance, and ensure low latency and safety guardrails while aligning with