About Ema

Ema builds AI Employees for HR, IT and Finance. Our AI Employees take on the busy work across the employee experience, from recruiting, onboarding and benefits to IT support, invoice processing and payroll, so people can spend their time on work that needs them. Founded by former executives from Google, Coinbase, Flipkart, and Okta, our team includes engineers from premier tech companies and graduates of Stanford, MIT, UC Berkeley, CMU, and IITs.

We are backed by industry leading investors including Accel, Naspers/Prosus, Creaegis, Section32, and angels like Sheryl Sandberg and Dustin Moskovitz. Headquartered in Silicon Valley and with offices in London, Bangalore and Vancouver, Ema is at the frontier of what Agentic AI can do in production. We ship real systems that run real business processes at scale.

Ema builds AI agents that act on sensitive enterprise data and systems. You’ll make sure the agents, and the platform they run on, are secure by design. You’ll build security controls for autonomous agents operating across multi-tenant enterprise environments, including cloud, on-prem and air-gapped deployments. You’ll solve zero-trust problems where the code isn’t static logic but non-deterministic models making live API calls against sensitive customer data. Our agents orchestrate 100+ LLMs, call third-party tools through MCP, execute code in sandboxes and drive headless browsers, and each of those is an attack surface you’ll help define.

Role Overview

What you’ll own

AI and agent security

• Threat model new AI agent features before launch: direct and indirect prompt injection, jailbreaks, data exfiltration through agent outputs, and over-privileged tool use

• Design guardrails for agentic workflows: least-privilege tool and connector scopes, human-in-the-loop approvals for high-risk actions, and output filtering

• Enforce tenant and data isolation across retrieval (RAG), context stores, and model calls, so no customer’s data leaks into another’s context

• Secure the AI supply chain: model and provider vetting, third-party MCP servers and connectors, prompt and config versioning

• Run AI red-team exercises and build automated adversarial tests (prompt injection suites) into CI

Cloud and platform security

• Security baselines for Kubernetes and cloud infrastructure: RBAC, network policies, workload identity, secrets management, per-tenant network isolation

• Security in CI/CD: IaC scanning, SAST and dependency scanning, policy-as-code guardrails