Senior AI Security Engineer
UNIVERSAL Technologies is seeking a Senior AI Security Engineer for a hybrid position in New York, NY supporting the MyCity Portal initiative. Candidates with an active LinkedIn profile are preferred.
Position:
The Senior AI Security Engineer will play a critical role in testing, evaluating, and securing GenAI systems integrated into the MyCity platform. This includes designing security architectures, conducting vulnerability assessments, building mitigation strategies, and ensuring compliance with ethical and inclusive AI development practices. The position is highly collaborative and requires a deep understanding of both cybersecurity and artificial intelligence technologies.
WHO WE ARE:
UNIVERSAL Technologies, LLC is a Women-Owned (M/WBE) IT solutions and consulting company focused on delivering enterprise systems that significantly improve our clients’ IT performance. We work across the IT spectrum including Development, Business/Systems/Data Analysis, Project Management, Cyber Security, Network Engineering, and High-Level System Architecture.
The pride in the services we provide and the accessibility and flexibility we offer to employees are what make UNIVERSAL Technologies stand out from the rest. We aim to propel your IT career to the next level and excite our employees with new and challenging projects.
WHAT WE OFFER:
Our W2 employees can expect the following benefits:
Competitive pay
Health/Dental Insurance
Group Life Insurance
401K
HSA/FSA
Pre-Tax Transportation Program
Generous Paid Time Off/Holiday Policy
KEY RESPONSIBILITIES:
Design, implement, and execute security tests for GenAI systems like the MyCity Chatbot
Perform functional, regression, performance, and usability testing on AI/ML models
Create and maintain test plans and strategies for AI/LLM applications
Conduct and document security assessments, threat modeling, and AI security design reviews
Develop and implement security reference architectures and mitigation strategies
Provide full-stack architecture reviews for GenAI platforms in cloud and on-prem environments
Collaborate with data science teams on NLP, LLMs, and security vulnerabilities
Identify and document flaws, irregularities, or inconsistencies in AI systems
Evaluate and enhance the quality of data used in model training and testing
Ensure compliance with ethical standards, including bias mitigation and inclusivity in AI design
Work with developers and cybersecurity practitioners on vulnerability remediation
Contribute to cross-functional teams focused on secure AI/ML deployments
Conduct ongoing research into AI risks, develop mitigations, and lead red team engagements
Perform prompt injection testing, input/output security analysis, and AI assurance activities
MANDATORY QUALIFICATIONS:
Bachelor’s degree in Computer Science, Engineering, Statistics, or related field, or equivalent work experience
12+ years of hands-on experience in cybersecurity or information security
4+ years of experience programming with Python and the standard ML stack (TensorFlow, PyTorch, NumPy, Pandas)
4+ years working with NLP and Large Language Models (LLMs)
4+ years working in cloud environments (Azure, AWS, GCP)
Demonstrated proficiency with AI/ML concepts, including deep learning and computer vision
Expertise in attacking GenAI platforms and identifying platform-specific vulnerabilities
Hands-on experience with AI testing frameworks and tools (TensorFlow, PyTorch, Keras)
Ability to write automated test scripts, analyze results, and document findings
Experience conducting security assurance, data validation, and AI system testing
Strong independent learning ability and adaptability to evolving technology
Excellent verbal and written communication skills, including ability to translate complex concepts
DESIRABLE QUALIFICATIONS:
Strong problem-solving and critical thinking skills in dynamic environments
Background in security architecture design, threat modeling, and mitigations
Past participation in CTFs, AI red teaming, bug bounty programs, or OSS AI security projects
Understanding of ML lifecycle, MLOps, and full AI model pipeline
Experience ensuring data quality during preprocessing, training, and testing phases
Ability to assess and mitigate AI bias, ethical risks, and promote inclusivity in development
Experience leading cross-functional AI/ML security teams, including LLM-based initiatives
Willingness to learn new technologies and stay up to date with trends in GenAI and cybersecurity
UNIVERSAL Technologies is an Equal Opportunity Employer.