SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 180,000 - 220,000 / annual
Artemis is building AI-driven defense technology to help companies detect and defend against sophisticated cyber threats in an era where AI systems are both attackers and defenders. The company is backed by First Round Capital and Brightmind, with founders from Palo Alto Networks, AWS, Demisto, Abnormal Security, and Twitter. The team includes engineers and researchers from Google, Abnormal AI, Wiz, Meta, AWS, CERN, and SentinelOne.
As an Offensive Security Engineer, you will design and build scalable adversary emulation scenarios that reproduce realistic attacker behaviors and multi-stage attack chains across cloud, identity, endpoint, SaaS, AI, and data environments. You'll validate detection capabilities end-to-end by tracing emulated activity through collection, normalization, enrichment, detection, and investigation workflows, identifying missed detections and visibility gaps.
Key responsibilities include researching attacks against AI systems (prompt injection, MCP and tool abuse, retrieval poisoning, excessive agent privileges) and data planes (service identity abuse, integration tokens, permissions, data access across databases and warehouses). You'll reproduce emerging exploits in isolated labs, assess vulnerability disclosures, and translate findings into detection hypotheses and bounded emulations.
You will enable safe testing in customer environments by building authorized emulations with clear scope, preflight checks, least-privilege access, execution limits, and verified cleanup. You'll build continuous validation by integrating scenarios with detector tests and engineering workflows, developing AI evaluation harnesses with attack variations and benign controls.
You'll partner with detection engineers, SOC teams, and customers to run purple-team exercises, explain findings and limitations, and provide analysts with evidence and guidance. Your work will directly improve how companies detect and defend against emerging threats, bridging research discoveries into practical defensive improvements.
REQUIREMENTS:
- 5+ years of hands-on cybersecurity experience with substantial offensive security, red teaming, adversary emulation, or security research work (equivalent demonstrated expertise accepted)
- Strong Python skills and track record building reusable security tools with APIs, SDKs, Git, code review, and automated testing
- Deep practical expertise in at least one cloud or identity ecosystem, with understanding of permissions, service identities, sessions, and data access
- Practical web/API security knowledge and experience chaining weaknesses across authorization boundaries into meaningful attack paths
- Experience reproducing attacks in controlled environments and connecting resulting behavior to audit logs, detection logic, and investigation evidence
- Experience assessing AI applications or agent workflows, or demonstrated offensive research into these systems
- Sound judgment in sensitive environments: define scope, anticipate side effects, limit impact, protect data, verify cleanup
- Clear communication and ability to own work from research through implementation, operational use, and verified outcomes
BONUS:
- Experience with Atomic Red Team, MITRE ATT&CK and ATLAS, purple teaming, or continuous security validation
- Experience with SQL, detection-as-code, and cloud, identity, SaaS, or endpoint telemetry
- Hands-on work with MCP servers, RAG systems, model gateways, or repeatable AI evaluations
- Experience assessing data warehouses, object storage, Kubernetes, CI/CD systems, or software supply chains
- Contributions to offensive tooling, emulation frameworks, detection content, or published security research
- Experience building isolated labs and enabling customers to operate security tooling
