onsite
Knowledge Engineer - Generative AI Platform and Cortex - Peraton
AI Engineer
Design and implement knowledge‑graph pipelines and generative AI services for a cutting‑edge Cortex platform, leveraging LLMs, prompt engineering, and cloud infrastructure to deliver mission‑critical insights.
About the role
Key Responsibilities
- Develop and maintain knowledge‑graph ingestion pipelines that integrate structured and unstructured data for the Generative AI platform.
- Design, fine‑tune, and evaluate Large Language Models (LLMs) to support domain‑specific prompt engineering and response generation.
- Implement scalable cloud‑native services (AWS/GCP) for model serving, data storage, and orchestration.
- Collaborate with data scientists, security engineers, and product owners to translate mission requirements into AI‑driven solutions.
- Establish best practices for model monitoring, versioning, and continuous improvement in a high‑security environment.
Requirements
- 5+ years of experience in AI/ML engineering, with a focus on LLMs, prompt engineering, or knowledge‑graph technologies.
- Proficiency in Python and associated ML libraries (e.g., PyTorch, TensorFlow, Hugging Face Transformers).
- Hands‑on experience deploying AI workloads on cloud platforms such as AWS or Google Cloud, including containerization and CI/CD pipelines.
- Strong understanding of Natural Language Processing techniques, data preprocessing, and model evaluation metrics.
- Excellent problem‑solving skills and ability to work in cross‑functional, security‑sensitive teams.
Skills
pythonmachine learningnatural language processing