Belmont Lavan is hiring an Agent Security Engineer to secure autonomous AI agents before and after they reach production. Agents now call tools, hold credentials and act on live systems, so they need the controls we already expect for people and services: identity, least-privilege access, monitoring and testing.
You will sit between AI engineering and security. You will design the guardrails, attack the systems yourself, and build the governance controls that let the business deploy agents with confidence.
Requirements
5+ years in security engineering (AppSec, cloud security, IAM or offensive security), with at least 1 year securing LLM or agent-based systems
Hands-on knowledge of LLM attack techniques: prompt injection, jailbreaks, data exfiltration via tools, RAG poisoning
... including Agent development, model risk, data protection, pipeline security, and misuse/abuse scenarios. - Bachelor's degree in Computer Science, Software Engineering, Information Security, or equivalent practical experience is preferred. - Security or cloud certifications (such as CSSLP, GWAPT, AWS/Azure Security, CKAD/CKS, ...
... expertise and security principles to strengthen browser isolation, proxy and gateway interception, and network-facing infrastructure. - Collaborate with AI and agent engineering teams to integrate AI agent capabilities and Model Context Protocol (MCP) servers into security solutions. - Develop supporting tools, detection ...
... serviços a um número considerável de clientes, operando em mais de 20 países. Job Description Mission Develop and evolve an autonomous pentesting platform based on agentic systems, integrated within the Offensive Security domain—specifically the Offensive Engineering and Innovation team—ensuring systems are effective, controllable, ...
... standards into automated checks in CI (policy as code, security scanning, schema-change gates, contract checks), because reviewers can't keep up with how much agents produce - Write runbooks and operational knowledge in a form both an engineer and an agent can follow, so agents can do first-pass incident triage and a human ...
... and IP/domain reputation. It runs on hundreds of thousands of shared, VPS and dedicated hosting servers, under cPanel, Plesk, DirectAdmin and standalone. The engineering org is 60+ engineers in squads covering backend, core, server agent, malware research, WAF/WebShield, and Patchman. Core services are Python; agents and ...
... demonstrations or isolated model integrations. - Identify opportunities to improve engineering productivity and product delivery through agentic development. - Mentor engineers and help shape an agentic-first technical strategy across the organization. - Collaborate with product and engineering leaders to connect agentic capabilities ...
... Mecatl is Stacklok’s open source, cloud-native agent harness. It provides the agent loop, tools, permissions, hooks, delegation, and durable sessions for running agents as production workloads on infrastructure you operate. As a Software Engineer II on the Mecatl team, you will build the platform that agents run on, and you ...
... Firecracker, Kata, or WASM runtimes – Interest in emerging ML infrastructure, edge inference, or browser-native models – Open-source contributions to LLM or agent infrastructure projects – Experience with identity, workload auth, or capability-based security systems. FULL-TIME EMPLOYEES AT COHERE ENJOY THESE PERKS: – A ...
... maintain internal SDKs to simplify LLM integration across teams. - Implement platform observability, monitoring, alerting, tracing, and evaluation of LLM and agent workflows, including latency, token usage, costs, and failovers. - Implement security and governance for LLM usage and AI agents. - Collaborate with internal ...