Principal Software Engineer, Perception Platform and AI Systems
$143k - $275k • United States, Washington, Redmond • Full-time
Posted 18d ago
Job Location
United States, Washington, Redmond
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
Microsoft Security is seeking a Principal Software Engineer to lead the evolution of the Perception Platform, an advanced AI platform designed to empower security and IT teams. This role involves driving foundational AI and platform investments, defining architecture and engineering strategy for sophisticated Generative AI, RAG, memory, reasoning, agentic and multi-agent systems, identity, AI safety, and distributed cloud platforms within enterprise security environments. The engineer will establish architectural patterns for secure, reliable, compliant, and scalable AI-powered experiences, working across organizational boundaries to translate business needs into technical architectures and align senior technical leaders.
Responsibilities
- Define the architecture and long-term technical strategy for enterprise AI platform capabilities including generative AI, retrieval, memory, reasoning, agent orchestration, model interaction, execution, evaluation, extensibility, security, and safety.
- Architect production-grade AI and RAG systems covering data ingestion, indexing, embeddings, retrieval, context construction, grounding, provenance, re-ranking, and evaluation.
- Design enterprise AI memory and knowledge architectures for conversational context, durable memory, organizational knowledge, and retrieved information, addressing authorization, provenance, freshness, retention, correction, deletion, and compliance.
- Architect agentic and multi-agent AI systems supporting planning, reasoning, tool use, task decomposition, delegation, collaboration, state 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, RBAC, delegated authorization, least-privilege access, multi-tenant isolation, and secure propagation of identity and authorization context.
- Establish security, safety, and execution guardrails against prompt injection, malicious 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 validated against 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 AI capabilities, risks, and enterprise requirements into scalable architectures, balancing quality with reliability, latency, cost, security, safety, and operational complexity.
- Provide Principal-level technical leadership across Microsoft Security AI platform investments, driving architectural convergence, reusable APIs and frameworks, reference architectures, technical design reviews, foundational investments, and alignment across organizations, while mentoring senior engineers and technical leaders.
Requirements
- Bachelor's Degree in Computer Science or related technical field AND 6+ years of technical engineering experience with coding in languages including C, C++, C#, Java, Go, JavaScript, or Python, OR equivalent experience.
- Ability to meet Microsoft, customer and/or government security screening requirements.
