Senior Software Architect Secure AI Agent Access Platform (Python)

Were building foundational infrastructure to secure AI agents including their identities, access patterns, and interactions with sensitive systems and data. This includes designing intelligent, dynamic mechanisms for ephemeral access control, secrets management, and agent/user identity tailored to modern agent frameworks such as LangChain, LangGraph, Semantic Kernel, AutoGen, and beyond.
Youll help define how agents (both machine and human-facing) authenticate, receive scoped access, perform actions securely, and leave behind a verifiable audit trail.
This is a unique opportunity to be part of a start-up inside the company building the platform from scratch at one of the most cutting-edge intersections of AI, identity, and security.
Responsibilities:
Lead the end-to-end architecture for secure infrastructure enabling AI agent access, identity, and action management.
Design and oversee the implementation of a secure access control and orchestration layer, covering secrets, tokens, API keys, credentials, and broader identity primitives.
Design and build systems that securely manage agent and user identities, delegate access intelligently and enforce real-time, context-aware permissions all while supporting high scalability and multi-agent concurrency.
Build policy and enforcement mechanisms for just-in-time access, TTL-based credentials, and role-bound permissions.
Collaborate with engineers to build agent-aware SDKs and wrappers that securely interface with tools, APIs, and services.
Define APIs, protocols, and data flows that are auditable, scalable, and secure by design.
Work cross-functionally with security, product, DevOps, and platform teams to shape cohesive solutions.
Establish coding and design standards, lead reviews, and mentor senior engineers.