Principal LLM Application Engineer

system_two; Palo Alto (CA); Remote; USD 180,000 - 260,000; Full time

Benefits offered by this job

Medical, Dental, Vision

Equity in the company

Job summary

System Two Security is seeking a Principal LLM Application Engineer to push the frontiers of LLMs and GenAI in cybersecurity. You will own technical leadership, architect scalable AI/ML capabilities, and collaborate across ML engineers, data scientists, and product teams.

You will implement RAG, function calling, and code interpreter tech, while shaping the roadmap and mentoring peers in a dynamic micoservices environment.

Qualifications

• Bachelor’s degree in a relevant field and 5+ years in NLP/ML.
• Experience with large language models and ML Ops workflows.
• Strong Python skills and cloud familiarity.

Responsibilities

• Develop and optimize LLMs for security-focused use cases.
• Evaluate model performance against accuracy and latency goals.
• Integrate RAG, function calling, and code interpretation features.
• Research ML advances and apply to product roadmaps.
• Lead data/model parallel training initiatives for scale.
• Collaborate with ML engineers, data scientists, and product teams.
• Document methodologies, results, and architectural decisions.
• Contribute to product vision and strategic tech choices.
• Design, test and deploy ML models and pipelines at scale.
• Mentor junior team members and share best practices.

Skills

NLP

ML Ops

Python

LLMs

Cloud infra

Education

Bachelor's degree in CS/Engineering

Tools

PyTorch

TensorFlow

Transformers

Job description

View all jobs Principal LLM Application Engineer Remote, United States Engineering Remote Full-time About System Two Security System Two Security is driving SOC transformation with its unique application of AI computing with an initial focus on generative AI powered proactive threat research, threat analysis and iterative threat hunting. The product’s purpose-built language agents respond to new threat actors and attack patterns within minutes with its agentic workflows delivering end-to-end threat detection and containment from integrated feeds of raw cyber threat advisories. Early users of the product include prominent MSSPs, and enterprise SOCs across retail, healthcare, SaaS and technology verticals. It is based in Palo Alto, CA and is venture funded by The Hive.

Job Description

System Two Security is looking to hire a Principal LLM Application Engineer where you will focus on leveraging and optimizing Large Language Models (LLMs) along with the implementation of advanced AI technologies. You will be working on cutting edge projects, and will utilize skills in GenAI, LLM and ML Ops to bring a better experience to customers. You will have the opportunity to be a technical leader and to take ownership for projects. It offers a significant opportunity for professional growth at the forefront of AI in the dynamic field of cybersecurity.

Responsibilities

• Development and Optimization of LLMs:Implement and fine-tune state-of-the-art Large Language Models for various applications, focusing on performance and accuracy.
• Evaluating Model Performance:Conduct rigorous evaluations of LLMs, assessing effectiveness, efficiency, and business alignment.
• Integration of Advanced AI Technologies:Implement Retrieval-Augmented Generation (RAG), function calling, and code interpreter technologies to enhance the capabilities of Large Language Models.
• Research and Development:Stay abreast of the latest advancements in machine learning, particularly in LLMs, LLM agents, and large-scale neural network training.
• Data and Model Parallel Training:Utilize data and model parallel training techniques for efficient handling of large-scale models.
• Cross-Functional Collaboration and Leadership:Work with ML engineers, data scientists, and product teams, providing guidance and mentorship.
• Documentation and Reporting:Maintain detailed documentation of methodologies, models, and results, communicating findings across the organization.
• Contribute to product roadmap and vision
• Implement and evaluate various LLM application logic ( flows ) and prompting strategies and stay up to date with the latest advancements in this field
• Lead the incubation of new initiatives, architect scalable solutions, and drive strategic technology choices to develop and deliver AI/ML capabilities in a micoservcies architecture for our customers.
• Design, test, and deploy Machine learning models, including large-language models and build pipelines at scale for batch and real-time use cases.

Required Skills

• Bachelor's degree in Computer Science, Engineering, or related field.
• 5+ years of experience in natural language processing, machine learning, and/or data science.
• Experience in Python or R.
• Experience working with large language models, such as GPT-3+, LLAMA, or similar.
• Strong problem-solving skills and the ability to think creatively to identify new opportunities for LLMs in our products and services.
• Experience with one or more deep learning frameworks.
• A deep theoretical or empirical understanding of deep learning.
• Experience in building, testing and deploying machine learning models, including large language models.
• Strong analytical and debugging skills.
• Familiarity with cloud-based infrastructure and distributed computing.
• Experience with DevOps/MLOps/LLMOps.
• Ability to address complex challenges in model training and optimization.
• Effective communication skills for conveying technical concepts and collaborating with cross-functional teams.
• Passion for staying updated with the latest trends in AI and machine learning.

Preferred Skills

• Master's or PhD in Computer Science, AI, or related fields, with a focus on machine learning and natural language processing.
• Proficiency in programming languages such as Python or R.
• Working experience within Cyber Security.
• Experience in building GenAI solutions using RAG framework and building LLM Agentic applications is preferred.

Benefits

• Medical, Dental, and Vision
• Equity in the company