AI Security Engineer - AI & Agentic Security

Onward Search; Woonsocket (RI); Remote; USD 140,000 - 200,000; Part time

Benefits offered by this job

Medical, Dental, and Vision Insurance.

Life Insurance.

401(k) Program.

Commuter Benefit.

eLearning and Ongoing Training.

Education Reimbursement.

Job summary

Onward Search is hiring an AI Security Engineer for AI & Agentic Security in a remote, temporary assignment. You will guide secure adoption of chatbots, GenAI, and agentic workflows by translating evolving risks into policies, controls, and practical guidance.

You will also support threat tracking, incident response, and compliance. The role requires strong software engineering (5+ years) with Python, plus 3+ years in AI/ML security, and familiarity with NIST AI RMF, MITRE ATLAS, and OWASP Top

Qualifications

• 5+ years of software engineering experience with Python or an equivalent language.
• 3+ years in AI/ML or GenAI security, or security with an AI focus.
• Knowledge of prompt injection, jailbreaking, unsafe outputs and agentic risk controls.
• Cloud security across two of AWS, GCP or Azure with related tooling; familiarity with OAuth 2.0/OIDC and mTLS.
• Ability to write testable security requirements and translate them to automated controls; HIPAA/compliance exposure.

Responsibilities

• Provide risk-based security guidance for chatbots, RAG, copilots, fine-tuning, and agentic workflows.
• Develop testable AI security policies and enforce via policy-as-code, CI/CD gates, gateway controls, and DLP.
• Track emerging AI tools, protocols, frameworks, vulnerabilities, and threats to provide timely security recommendations.
• Design and operate protections across AI/ML/GenAI/agentic systems, including guardrails against prompt injection and data leakage.
• Support threat modeling, incident investigations, detection engineering, compliance activities, and vendor evaluations.

Skills

Python

AI/ML security

Cloud security

Tools

AWS security tooling

OAuth 2.0/OIDC

mTLS

Job description

We are hiring an AI Security Engineer -- AI & Agentic Security, a temporary opportunity, for our client. This is a remote, out-of-region role. This position guides secure adoption of chatbots, GenAI, and agentic workflows by translating evolving risks into policies, controls, and practical security guidance. It also supports gateway security, threat tracking, incident response, and compliance.

There is no application deadline for this role.

AI Security Engineer -- AI & Agentic Security Responsibilities:

• Provide risk-based security guidance for chatbots, RAG, copilots, fine-tuning, and agentic workflows.
• Develop testable AI security policies and implement automated enforcement through policy-as-code, CI/CD gates, gateway controls, and DLP.
• Track emerging AI tools, protocols, frameworks, vulnerabilities, and threats to provide timely security recommendations.
• Design and operate protections across AI, ML, GenAI, and agentic systems, including guardrails for prompt injection, unsafe outputs, unauthorized tool execution, and data leakage.
• Support threat modeling, incident investigations, detection engineering, compliance activities, vendor evaluations, and AI security reference architecture.

AI Security Engineer -- AI & Agentic Security Qualifications:

• Strong software engineering experience, including at least 5 years of experience and proficiency in Python or an equivalent programming language.
• At least 3 years of AI/ML or GenAI security experience, or equivalent hands-on information security experience with a demonstrated transition into AI security.
• Working knowledge of prompt injection, jailbreaking, unsafe outputs, tool-use abuse, identity misuse, agentic workflow escalation, and frameworks including NIST AI RMF, MITRE ATLAS, and OWASP LLM or Agentic Top 10.
• Experience with cloud security across at least two of AWS, GCP, and Azure, including native AI/ML security tooling, plus familiarity with OAuth 2.0/2.1, OIDC, mTLS, and workload or non-human identity concepts.
• Demonstrated ability to write specific, testable security requirements, translate them into automated controls, independently evaluate emerging technologies, and work within HIPAA or equivalent compliance obligations.

Perks and Benefits:

• Medical, Dental, and Vision Insurance.
• Life Insurance.
• 401(k) Program.
• Commuter Benefit.
• eLearning and Ongoing Training.
• Education Reimbursement.

Eligibility requires working over 30 hours per week on an assignment lasting at least 10 weeks.