Principal Software Engineer Perception Platform And AI Systems United States Washington Redmond

Job description

Define the architecture and long-term technical strategy for enterprise AI platform capabilities spanning generative AI, retrieval, memory, reasoning, agent orchestration, model interaction, execution, evaluation, extensibility, security, and safety. Architect production-grade AI and Retrieval-Augmented Generation (RAG) systems, including data ingestion, indexing, embeddings, semantic and hybrid retrieval, context construction, grounding, provenance, re-ranking, and retrieval evaluation. Design enterprise AI memory and knowledge architectures that manage conversational context, durable memory, organizational knowledge, and retrieved information while addressing authorization, provenance, freshness, retention, correction, deletion, and compliance requirements. Architect agentic and multi-agent AI systems that support planning, reasoning, tool use, task decomposition, delegation, collaboration, state and memory management, human-in-the-loop patterns, failure recovery, and bounded autonomous execution. Define identity, authentication, and authorization architectures for AI agents, including user, workload, service, and agent identities; Role-Based Access Control (RBAC); delegated authorization; least-privilege access; multi-tenant isolation; and secure propagation of identity and authorization context across distributed workflows. Establish security, safety, and execution guardrails that protect AI systems against prompt injection, malicious or untrusted content, unsafe tool invocation, data exfiltration, privilege escalation, unauthorized delegation, excessive agency, and cross-tenant access. Design AI architectures that enforce authorization and trust throughout retrieval and execution, ensuring agents access only permitted data and that AI-generated plans, decisions, and tool calls are independently validated against applicable security, authorization, safety, and compliance policies. Establish end-to-end reliability, evaluation, and observability frameworks for distributed AI systems, covering retrieval and model quality, grounding, agent behavior, authorization decisions, tool execution, task completion, safety, telemetry, regression detection, failure recovery, and graceful degradation. Partner across engineering, research, product, security, privacy, and compliance organizations to translate evolving AI capabilities, risks, and enterprise requirements into scalable architectures and balance quality with reliability, latency, cost, security, safety, and operational complexity. Bachelor's Degree in Computer Science or related technical field AND 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, Go, JavaScript, or Python OR equivalent experience Master's Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, Go, JavaScript, or Python OR Bachelor's Degree in Computer Science or related technical field AND 12+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, Go, JavaScript, or Python OR equivalent experience. Extensive experience architecting, building, and operating large-scale distributed systems, cloud services, enterprise platforms, or AI platforms in production environments. Deep experience with Generative AI and AI systems architecture, including model orchestration, retrieval/RAG, semantic search, memory, context management, tool use, evaluation, safety, and production operationalization. Experience designing agentic and multi-agent AI systems, including planning, reasoning, orchestration, delegation, collaboration, state and memory management, tool use, long-running execution, and failure recovery. Experience establishing reusable engineering patterns, frameworks, and platform capabilities for reliable, secure, observable, and scalable AI and agentic systems. Deep experience designing identity, authentication, and authorization architectures for autonomous or agentic systems, including user, application, workload, service, and agent identities. Expertise in RBAC, policy-based and resource-level authorization, least privilege, scoped permissions, delegated authorization, and multi-tenant isolation, including securing delegation chains and preventing privilege escalation or unauthorized cross-tenant access. Demonstrated ability to provide technical leadership across complex, ambiguous initiatives, translating business, product, and security requirements into durable architectures, technical standards, and long-term engineering strategies across multiple teams or organizations. Demonstrated technical leadership and communication skills, with experience influencing architectural decisions across organizational boundaries, mentoring senior engineers, establishing engineering standards, and communicating complex technical decisions, risks, and tradeoffs to engineering and leadership audiences.