About the role

Please note, this team is hiring across all levels and candidates are individually assessed and appropriately leveled based upon their skills and experience.

In this role you will get the opportunity to spearhead the development of advanced GenAI/LLM Applications protection solutions. You will design and conduct technical research related to GenAI applications Security. You will collaborate with other internal engineering, product management, and AI/ML teams to develop and integrate innovative security capabilities into our platform. You will Design and lead technical security research and development in the field of GenAI applications Security. Join us to drive the next frontier in AI /LLM security ensuring robust defense against emerging threats.

What you will be doing

• Designing, Architecting and Developing high performance, scalable cloud based security systems and services. 
• Lead the design and  development of robust, secure, and scalable systems to detect and mitigate attacks on generative AI applications and LLMs.
• Conduct advanced coding for performance-sensitive areas, ensuring systems are highly reliable and secure under operational stress.
• Develop and apply techniques to detect and protect against model vulnerabilities, prompt injections, adversarial attacks, data poisoning, and other AI-specific threats.
• Research and integrate emerging tools and techniques for identifying vulnerabilities in LLMs and generative AI systems.
• Enhance system performance and scalability while maintaining rigorous security standards.
• Drive continuous improvements in code quality, system performance, and security.
• Partner with Product management, other engineering, research, and data science teams to identify, design, and implement best-in-class security features.
• Mentor junior engineers and guide best practices in secure development, code optimization, and performance tuning.
• Use advanced data structures and algorithms in C++, Python.

Required skills and experience

• 10+ years of experience building high-performance security software in a distributed environment 
• Programming mastery in C++ and experience in Python a plus
• Solid understanding of algorithms and data structure to implement real-time inline data processing
• Strong understanding of computer architecture – multi-threading, CPU scheduling and memory management
• Good knowledge of Linux at the system level
• Experience in network and web/content security technologies (LLM/Gen AI security, Advanced threat protection, Web Security, NGIPS, Protocol and User Anomaly detections, etc.)
• Knowledge of machine learning frameworks and LLM structures is a strong plus.
• Experience with Unit Testing frameworks - C++ gtest, pytest and CI/CD
• Experience with No-SQL databases like MongoDB, Redis and cloud technologies like Kafka.
• Familiarity with GenAI technologies, experience in security research e.g. AI/Machine learning, AppSec\cloud security, LLM, Adversarial attacks and Jail-breaking methods are big plus
• Excellent analytical and problem-solving skills, coupled with discretion and sound independent judgment
• Self-starter with desire to work in a fast paced environment with cross-timezone teams
• Candidates should have an attitude of “go and get it done” and should exhibit it in day-2-day work
• Excellent verbal and written communication skills

Education

• Minimum BSCS or equivalent required
  
  

#LI-SC3