Key Responsibilities
1) Design, develop, and optimize GPT-based solutions for cyber security use cases.2)Engineer advanced prompt frameworks, system instructions, and guardrails to ensure accurate, consistent, and secure model outputs.3)Develop and manage retrieval-augmented generation (RAG) pipelines, embedding strategies, and contextual memory architectures to improve model relevance and domain specificity.4)Fine-tune and evaluate LLM performance using structured datasets aligned with cyber security workflows.5) Integrate GPT-based capabilities into security platforms such as SIEM, SOAR, CTI platforms, and ticketing systems (e.g., Sentinel, XSOAR, Service Now).Build automated pipelines for model validation, performance bench-marking, hallucination reduction, and output quality scoring.6) Collaborate closely with cyber security operations teams (SOC, IR, CTI, VM) to translate operational challenges into scalable AI-driven solutions.7)Implement responsible AI controls, including data privacy, prompt injection protection, role-based access controls, and output validation mechanisms.Continuously monitor production model performance and refine outputs through feedback loops and telemetry-based optimization.8) Strong hands-on experience working with transformer-based models (GPT or equivalent LLMs).9)Advanced prompt engineering expertise including structured prompts, system conditioning, chain-of-thought prompting, and role-based context design.Experience building or implementing RAG (Retrieval-Augmented Generation) architectures.10) Familiarity with embeddings, vector databases, semantic search, and context optimization.Understanding of fine-tuning workflows, model evaluation metrics, and bias mitigation strategies.11) Experience working with OpenAI APIs or equivalent LLM APIs in production environments is a plus.12) Strong proficiency in Python for AI development and automation.Understanding in ML/NLP frameworks such as PyTorch, TensorFlow, Hugging Face Transformers, or similar.13) Ability to preprocess, structure, and manage large security datasets for model training and evaluation.14) Experience building API integrations and automation workflows.Ability to design scalable AI solutions that operate reliably in enterprise environments.15) Strong troubleshooting and root-cause analysis capabilities for model inconsistencies.16) Capability to translate complex security data into clear, structured, executive-ready outputs.We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses.
These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.Apply for this job
