Senior Backend Engineer - AI

Job summary

We are building the trust layer for the agentic future. As AI agents move from simple chatbots to autonomous workloads with access to sensitive enterprise data, the industry lacks a standard for Identity, Authentication, and Governance.

You will architect and build the core security and identity infrastructure that defines how AI agents are identified, authenticated, authorized, and governed at scale. You will set foundational architectural patterns, establish engineering standards, and help shape the long-term technical vision of the company.

This is a hands-on technical leadership role in a high-ownership startup environment.

What you will do

Architect the Trust Layer for AI

• Design and implement distributed identity and authorization systems for autonomous AI agents.
• Define Zero Trust principles for agent-to-agent and agent-to-system communication.
• Architect cryptographic identity, verifiable credentials, and secure delegation models.

Build Cloud-Native, SaaS Infrastructure

• Design and ship production-grade, multi-tenant SaaS services.
• Build containerized microservices (Kubernetes-based) with strong observability, scalability, and resilience.
• Establish secure service-to-service communication patterns using modern cloud-native best practices.

Develop Agent Security Testbeds

• Build sophisticated multi-agent workflows to stress-test identity boundaries and governance models.
• Create adversarial test harnesses to simulate prompt injection, privilege escalation, data exfiltration, and confused deputy attacks.
• Ensure the platform is resilient against real-world enterprise attack scenarios.

Design Secure Developer SDKs

• Create developer-facing SDKs and APIs that embed secure identity primitives into AI workloads.
• Ensure clean abstractions and seamless integration into enterprise systems.

Secure Tooling & Protocol Architecture

• Architect how agents interact securely with external systems via MCP or custom tool protocols.
• Ensure every tool invocation is authenticated, authorized, and fully auditable.
• Define policy enforcement layers for tool execution and resource access.

Technical Leadership

• Own architectural direction and long-term technical roadmap.
• Establish engineering standards for security, reliability, and performance.
• Partner with infrastructure, product, and security teams to align on scalable execution.
• Mentor engineers and raise the technical bar across the organization.

What you will have

Experience

• 12+ years of professional software engineering experience.
• Proven track record building and scaling cloud-native SaaS platforms.
• Experience designing distributed systems that operate at enterprise scale.
• Demonstrated ownership of zero-to-one or early-stage platform architecture.

Cloud & Infrastructure Expertise

• Deep experience with Kubernetes, containerization, and microservices.
• Strong background in AWS, Azure, or GCP (production environments).
• Experience building secure multi-tenant systems.
• Familiarity with service meshes, API gateways, and identity federation (OIDC/OAuth2).

Security & Identity Architecture

• Strong understanding of Zero Trust architectures.
• Experience designing authentication, authorization (RBAC/ABAC), and policy-driven systems.
• Familiarity with cryptographic primitives and secure token systems.
• Understanding of common security threats in distributed systems.

AI / Agent Ecosystem Experience

• Hands-on experience building or deploying LLM-based systems in production.
• Familiarity with frameworks such as LangGraph, CrewAI, or AutoGen.
• Experience deploying workloads on Azure AI Foundry, AWS Bedrock, or Vertex AI.
• Understanding of prompt injection risks, model safety, and tool security boundaries.

Note: Deep agentic AI tenure is not required, but demonstrated production experience with LLM-powered systems is expected.

Software Engineering Excellence

• Expert-level Python (FastAPI, Pydantic, AsyncIO).
• Strong API design principles and SDK development experience.
• Writes modular, production-grade code intended for reuse by other developers.
• Strong testing discipline (unit, integration, adversarial testing).

Startup Mindset

• Comfortable operating in ambiguity.
• Experience owning architecture, implementation, and reliability simultaneously.
• Bias toward shipping and iterative improvement.

Benefits

• Generous time off policies
• Top shelf benefits
• Education, wellness and lifestyle support

#LI-RR1