AI Security Researcher - Adversarial & Agentic Safety

Cisco Systems, Inc.

San Francisco (CA)

On-site

USD 257,000 - 384,000

Full time

3 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Cisco Systems, Inc. in San Francisco seeks a leader in AI threat intelligence and security research to advance adversarial AI, agentic systems, and security in production platforms.

You will design robust guardrails and collaborate with product teams to translate research into enterprise protections. Ideal candidates have extensive AI/ML security experience, knowledge of MITRE ATLAS, OWASP for LLMs, and strong Python/Go and ML framework skills.

Qualifications

  • 12+ years of related experience with a Bachelor’s degree, or 8+ years with a Master’s, or 5+ years with a PhD.
  • 5+ years in AI/ML security research and related fields.
  • Strong knowledge of transformer models, RAG, and evaluation benchmarking.
  • Experience mapping threats to security frameworks (MITRE ATLAS, OWASP for LLMs).
  • Proficient in Python, Go, PyTorch/TensorFlow; large-scale data handling.

Responsibilities

  • Lead research on adversarial AI and agentic systems.
  • Architect robust agentic security frameworks and guardrails.
  • Design and deploy automated threat detection models and telemetry.
  • Conduct adversarial red-teaming and safety benchmarking across models.
  • Partner with product and engineering to translate findings into capabilities.

Skills

AI/ML security
Adversarial ML
Python/Go
PyTorch/TensorFlow
Threat intelligence

Education

Bachelor's degree
Master's degree
PhD

Tools

Kubernetes
Helm
Snowflake
Spark
Kafka
MCP
LangChain
LlamaIndex

Job description

Cisco Systems, Inc. in San Francisco seeks a leader in AI threat intelligence and security research to advance adversarial AI, agentic systems, and security in production platforms.

You will design robust guardrails and collaborate with product teams to translate research into enterprise protections. Ideal candidates have extensive AI/ML security experience, knowledge of MITRE ATLAS, OWASP for LLMs, and strong Python/Go and ML framework skills.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior Adversarial AI Security Researcher
Senior Adversarial AI Security Researcher

020 Cisco Systems, Inc. • San Francisco (CA)

On-site
USD 257,000 - 333,000
Lead AI Security Researcher (Threat Intel)
Lead AI Security Researcher (Threat Intel)

Cisco • Milpitas (CA)

On-site
USD 257,000 - 333,000
Bonus program
Health insurance
401(k) plan
+1
Lead AI Security Researcher: Adversarial & Agentic Defense
Lead AI Security Researcher: Adversarial & Agentic Defense

Cisco Systems, Inc • Washington

On-site
USD 257,000 - 333,000
Medical, dental and vision insurance
401(k) with Cisco matching
Paid parental leave
+3
AI Security Research Lead
AI Security Research Lead

Carnegie Mellon SEI • Pittsburgh

On-site
USD 140,000 - 190,000
Principal AI Security Architect
Principal AI Security Architect

Cisco • San Jose (CA)

Hybrid
USD 202,000 - 272,000
AI Security Research Scientist — Innovate Safe AI Systems
AI Security Research Scientist — Innovate Safe AI Systems

Remote Jobs • Seattle (WA)

On-site
USD 168,000 - 305,000
Equity
Benefits
Principal AI Security Architect
Principal AI Security Architect

Cisco Systems, Inc • Austin (TX)

Hybrid
USD 202,000 - 272,000
Principal AI Defense Engineer — Enterprise AI Security
Principal AI Defense Engineer — Enterprise AI Security

Cisco Systems, Inc • Milpitas (CA)

Hybrid
USD 251,000 - 363,000
Hybrid work
Principal AI Security Architect
Principal AI Security Architect

Cisco Systems, Inc • San Jose (CA)

Hybrid
USD 202,000 - 272,000
AI Security Researcher & Red Team Architect
AI Security Researcher & Red Team Architect

Webhosting • Austin (TX)

Hybrid
USD 180,000 - 280,000
Equity plan