Job Description
Job Title: Agentic Workflow Engineer (Cybersecurity)
\n
Type of Engagement: Contract
\n
Location: Juno Beach, FL
\n
\n
Responsibilities:
\n
- \n
- Design, develop, and deploy AI-powered agentic workflows to automate cybersecurity operations.
- Build production-grade AI agents using Python, LLMs, RAG, and orchestration frameworks such as LangChain, LangGraph, CrewAI, or similar.
- Develop multi-step reasoning workflows that leverage AI agents capable of using enterprise tools and APIs.
- Integrate AI solutions with cybersecurity platforms including SIEM, SOAR, EDR, IAM, ticketing systems, and other internal security tools.
- Build Retrieval-Augmented Generation (RAG) pipelines using enterprise security documentation, playbooks, and knowledge bases.
- Develop secure APIs and integrate AI agents using Model Context Protocol (MCP) or standard REST APIs.
- Collaborate with Threat Hunting, Incident Response, Vulnerability Management, IAM, Compliance, and Security Operations teams to automate security workflows.
- Deploy, monitor, and optimize AI applications on AWS, including Amazon Bedrock or similar Generative AI platforms.
- Ensure AI workflows meet enterprise standards for security, governance, auditability, logging, and compliance.
- Perform LLM testing, evaluation, prompt optimization, and production support for scalable AI solutions.
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
Required Skills:
\n
- \n
- Strong hands-on experience with Python, including production-quality development, testing, packaging, and API development.
- Experience building Agentic AI applications using LangChain, LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, or similar frameworks.
- Strong understanding of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), prompt engineering, tool/function calling, and multi-agent workflows.
- Experience integrating AI applications with enterprise APIs and external tools.
- Working knowledge of cybersecurity concepts including Threat Hunting, Incident Response, SIEM, SOAR, EDR, IAM, Vulnerability Management, and Compliance.
- Experience with AWS services, especially Amazon Bedrock or other cloud-based Generative AI platforms.
- Knowledge of secure software development, secrets management, logging, monitoring, and enterprise governance.
- Strong understanding of scalable system design and deploying AI applications into production environments.
- Excellent problem-solving, communication, and cross-functional collaboration skills.
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
Preferred Skills:
\n
- \n
- Experience integrating with Splunk, Microsoft Sentinel, QRadar, CrowdStrike, SentinelOne, Cortex XSOAR, ServiceNow, Jira, or similar security platforms.
- Experience with Model Context Protocol (MCP).
- Hands-on experience evaluating LLM performance, hallucination testing, prompt evaluation, and AI quality metrics.
- Experience with Vector Databases such as Pinecone, FAISS, Weaviate, ChromaDB, or Milvus.
- Familiarity with Docker, Kubernetes, CI/CD pipelines, and enterprise cloud deployments.
- Experience building secure, compliant AI applications within regulated enterprise environments.
\n
\n
\n
\n
\n
\n
\n
\n
Additional Information:
\n
- \n
- Strong experience in Python, Generative AI, Agentic AI, LLMs, RAG, LangChain/LangGraph/CrewAI, AWS, and Cybersecurity Automation is required.
- Candidates with experience building production-ready AI agents, integrating enterprise security tools (SIEM/SOAR/EDR), automating SOC workflows, and deploying secure AI solutions in regulated environments are highly preferred.
\n
\n
\n