Lead AI Security Engineer

GoTo Foods, LLC; Atlanta (GA); Hybrid; USD 120,000 - 180,000; Full time

Job summary

GoTo Foods, LLC is seeking a Lead AI Security Engineer to safeguard our AI/ML systems across the full lifecycle—design, development, deployment, monitoring, and incident response. You will collaborate with security, engineering, data science, product, privacy, legal, finance, and governance teams to identify and mitigate risks in AI applications, models, data pipelines, agents, prompts, and integrations.

The ideal candidate blends hands-on cybersecurity with practical AI/ML knowledge,

Qualifications

• Practical understanding of AI/ML concepts, including model training, inference, embeddings, vector databases, RAG architectures, model APIs, and evaluation workflows.
• Experience performing threat modeling, architecture reviews, secure design reviews, vulnerability assessments, or penetration testing for modern applications and cloud services.
• Familiarity with common AI security risks such as prompt injection, data leakage, unsafe tool use, model poisoning, adversarial examples, insecure outputs, and supply chain threats.
• Working knowledge of secure software development practices, authentication and authorization patterns, API security, secrets management, logging, and monitoring.
• Experience with at least one major cloud platform such as Microsoft Azure, AWS, or Google Cloud Platform.
• Ability to communicate technical risk clearly to engineering teams, leadership, product stakeholders, and non-security audiences.
• Strong analytical, problem-solving, documentation, and cross-functional collaboration skills.
• Experience securing generative AI applications, LLM-powered products, copilots, autonomous agents, or AI-assisted developer tools, preferred.
• Hands-on experience with AI security testing, red teaming, evaluation harnesses, model guardrails, content safety controls, or abuse monitoring, preferred.
• Knowledge of AI governance and risk management frameworks such as NIST AI RMF, OWASP Top 10 for LLM Applications, MITRE ATLAS, ISO/IEC 42001, or related guidance, preferred.
• Experience with DevSecOps, CI/CD security controls, SAST/DAST/SCA, container security, infrastructure as code scanning, and software supply chain security, preferred.
• Familiarity with Python, scripting, notebooks, ML frameworks, security automation, or data analysis workflows, preferred.

Responsibilities

• Secure AI/ML systems across the full lifecycle—from design and development through deployment, monitoring, and incident response.
• Partner with security, engineering, data science, product, privacy, legal, governance to identify and reduce risks associated with AI applications, models, data pipelines, agents, prompts, and integrations.
• Design and implement AI security controls, guardrails, logging, monitoring, and governance artifacts.
• Lead threat modeling, architecture reviews, secure design reviews, and security testing plans including red teaming, misuse-case validation, automated testing, and manual assessment techniques.
• Evaluate vendors, models, datasets, APIs, and infrastructure for security, privacy, compliance, and supply chain risk.
• Support incident response for AI-related security events, including anomalous model behavior, data exposure, abuse patterns, and unauthorized access.

Skills

AI/ML concepts

Threat modeling

Architecture reviews

Vulnerability assessments

Penetration testing

Prompt injection

Data leakage

Unsafe tool use

Model poisoning

Adversarial examples

Supply chain threats

Secure SDLC

Authentication patterns

API security

Secrets management

Logging

Monitoring

Cloud platforms

Risk communication

Analytical skills

Problem solving

Documentation

Cross-functional collaboration

LLM security

Generative AI security

Red teaming

Model guardrails

Content safety controls

Abuse monitoring

NIST AI RMF

MITRE ATLAS

ISO 42001

DevSecOps

CI/CD security

SAST/DAST/SCA

Container security

IaC scanning

Python

Scripting

ML frameworks

Security automation

Data analysis

Education

Bachelor's degree in STEM related field

Tools

Azure

AWS

Google Cloud Platform

Job description

• Develop and implement security requirements, controls, and review processes for AI/ML applications, models, data pipelines, and AI-enabled products.
• Perform AI-focused threat modeling, architecture reviews, and risk assessments for model training, fine-tuning, retrieval-augmented generation, inference, agent workflows, and third-party AI services.
• Evaluate AI systems for vulnerabilities including prompt injection, jailbreaks, data exfiltration, insecure tool/function calling, model inversion, poisoning, adversarial inputs, excessive agency, and unsafe output handling.
• Secure Architecture: Ability to design and evaluate secure AI system patterns, including model access control, data boundaries, tool isolation, and monitoring.
• Adversarial Mindset: Ability to think like an attacker and test how AI systems may be misused or manipulated.
• Partners with engineering and data science teams embed security into the AI development lifecycle, including secure design patterns, guardrails, logging, monitoring, and abuse-case testing.
• Design and execute security testing plans for AI applications, including red teaming,misusecase validation, automated testing, and manual assessment techniques.
• Assess AI vendors, open-source models, datasets, packages, APIs, and infrastructure dependencies for security, privacy, compliance, and supply chain risk.
• Support incident response for AI-related security events, including anomalous model behavior, data exposure, abuse patterns, compromised integrations, or unauthorized model access.
• Collaborate with privacy, legal, compliance, and governance stakeholders to support responsible AI practices, data protection, audit readiness, and regulatory obligations.
• Product Partnership: Ability to influence teams through practical guidance, reusable patterns, and clear risk-based recommendations.
• Track emerging AI security threats, frameworks, and industry guidance; translate learnings into practical controls and actionable recommendations.
• Define andmaintainAI security standards, secure coding guidance, model deployment checklists, and governance artifacts aligned with organizational risk appetite.
• AI Security Risk Assessment: Ability toidentify, prioritize, and mitigate AI-specific security risks across business-critical use cases.
• Continuous Learning: Commitment to staying current with fast-moving AI security research, tooling, standards, and threat intelligence.

What Success Looks Like

• AI security requirements and review processes are consistently adopted across AI-enabled products and services.
• High-risk AI threats are identified early and mitigated before production release.
• Security testing and red teaming results produce clear, actionable engineering improvements.
• AI vendors, datasets, models, and integrations are assessed through repeatable risk review processes.
• Security incidents and abuse signals involving AI systems are detected, investigated, and remediated effectively.

Job Summary

Lead AI Security Engineer is a mid-level individual contributor responsible to secure the organization’s artificial intelligence and machine learning systems across the full lifecycle—from design and model development through deployment, monitoring, and incident response. This role will partner with all business lines such security, engineering, data science, product, privacy, legal, finance, human resources, marketing, and governance teams to identify and reduce risks associated with AI applications, models, data pipelines, agents, prompts, and integrations.

The ideal candidate combines hands‑on cybersecurity experience with a practical understanding of AI/ML systems, cloud‑native architecture, secure software development, threat modeling, and emerging AI‑specific risks such as prompt injection, data leakage, model manipulation, insecure plugin/tool use, supply chain exposure, and unsafe agent behavior.

Workplace Type

Fixed Hybrid-Atlanta

Education

Bachelor's degree in STEM related field. Advanced degree is preferred. Non-degreed applicants with equivalent experience will be considered.

Work Experience

• Minimal 3+ years of experience in cybersecurity, application security, product security, cloud security, security engineering, or a related technical security role.
• Experience in AI security role, preferred.

Skills & Abilities

• Practical understanding of AI/ML concepts, including model training, inference, embeddings, vector databases, RAG architectures, model APIs, and evaluation workflows.
• Experience performing threat modeling, architecture reviews, secure design reviews, vulnerability assessments, or penetration testing for modern applications and cloud services.
• Familiarity with common AI security risks such as prompt injection, data leakage, unsafe tool use, model poisoning, adversarial examples, insecure outputs, and supply chain threats.
• Working knowledge of secure software development practices, authentication and authorization patterns, API security, secrets management, logging, and monitoring.
• Experience with at least one major cloud platform such as Microsoft Azure, AWS, or Google Cloud Platform.
• Ability to communicate technical risk clearly to engineering teams, leadership, product stakeholders, and non-security audiences.
• Strong analytical, problem-solving, documentation, and cross-functional collaboration skills.
• Experience securing generative AI applications, LLM-powered products, copilots, autonomous agents, or AI-assisted developer tools, preferred.
• Hands‑on experience with AI security testing, red teaming, evaluation harnesses, model guardrails, content safety controls, or abuse monitoring, preferred.
• Knowledge of AI governance and risk management frameworks such as NIST AI RMF, OWASP Top 10 for LLM Applications, MITRE ATLAS, ISO/IEC 42001, or related guidance, preferred.
• Experience with DevSecOps, CI/CD security controls, SAST/DAST/SCA, container security, infrastructure as code scanning, and software supply chain security, preferred.
• Familiarity with Python, scripting, notebooks, ML frameworks, security automation, or data analysis workflows, preferred.

Licenses/Certifications

Relevant certifications such as CISSP, CSSLP, CCSP, GSEC, GWAPT, OSCP, Azure Security Engineer, or equivalent practical experience.