SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Ema builds AI Employees for HR, IT, and Finance—autonomous agents that handle recruiting, onboarding, benefits, IT support, invoice processing, and payroll. Founded by former executives from Google, Coinbase, Flipkart, and Okta, the company is backed by Accel, Naspers/Prosus, and angels including Sheryl Sandberg and Dustin Moskovitz. Ema operates from Silicon Valley with offices in London, Bangalore, and Vancouver.
In this role, you will own security for AI agents and the platform they run on. Ema's agents orchestrate 100+ LLMs, call third-party tools via MCP, execute code in sandboxes, and drive headless browsers—each an attack surface requiring careful design.
You will focus on two core areas:
**AI and Agent Security:** Threat model new AI agent features before launch, including direct and indirect prompt injection, jailbreaks, data exfiltration through agent outputs, and over-privileged tool use. Design guardrails for agentic workflows such as 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 to prevent customer data leakage. Secure the AI supply chain through model and provider vetting, third-party MCP servers and connectors, and prompt and config versioning. Run AI red-team exercises and build automated adversarial tests (prompt injection suites) into CI.
**Cloud and Platform Security:** Establish security baselines for Kubernetes and cloud infrastructure including RBAC, network policies, workload identity, secrets management, and per-tenant network isolation. Implement security in CI/CD through IaC scanning, SAST and dependency scanning, and policy-as-code guardrails.
You will also contribute to AI-aware detection by logging prompts, tool calls, and agent actions, and alerting on anomalous agent behavior. You'll partner with the Security & Compliance Lead on technical controls and evidence for SOC 2 Type II, ISO 27001, HIPAA, and ISO 42001 compliance, plus the NIST AI RMF.
Reporting to the Security & Compliance Lead, you'll partner directly with Engineering and Product leadership, sitting in design reviews from day one with real influence over what ships. Security is treated as a core product feature, not a compliance checkbox.
**Requirements:**
- 5+ years in cloud security, application security, or DevSecOps (GCP/Azure preferred)
- Deep hands-on Kubernetes and cloud security experience
- Security automation with IaC (Terraform/Helm) and Python or Bash
- Working understanding of LLM application risks (OWASP Top 10 for LLM Applications) and how agentic systems fail
- Comfortable influencing engineers without formal authority
**Nice-to-haves:**
- Hands-on experience securing LLM, RAG, or agentic systems in production
- AI red teaming or familiarity with MITRE ATLAS
- CNAPP/CSPM tooling, SIEM/detection engineering
- Contributions to AI security research, open-source tools, or CTFs
