TC-CS-Cyber Architecture- OT and Engineering- Agentic AI security engineer-Senior

Sr. Agentic AI Engineer

Job Description

Cybersecurity is seeking a Sr. Agentic AI Engineer to join the Cyber Analytics and Data Science team. This role focuses on designing, building, and operationalizing agentic AI systems, multi-agent frameworks, and intelligent automation solutions that enhance our cybersecurity posture. The ideal candidate will leverage advanced machine learning, LLM engineering, reasoning systems, and data engineering to solve enterprise-scale problems and drive the next generation of autonomous cyber-analytics capabilities.

You will be directly responsible for the architecture, development, deployment, and automation of agentic AI applications that support predictive, prescriptive, and autonomous cybersecurity operations. This role partners closely with key stakeholders across Cybersecurity, IT, and Data Engineering to accelerate the adoption of multi-agent systems, RAG-enhanced intelligence, and enterprise AI platforms.

The Sr. Agentic AI Engineer is a hands-on technologist, creative problem solver, and trusted advisor who brings deep experience with emerging AI technologies and a passion for building scalable, production-grade autonomous systems.

Responsibilities

• Agentic AI & Multi-Agent System Development
  • Architect, design, and deploy agentic AI workflows using frameworks such as LangChain, LangGraph, AutoGen, and related orchestration libraries.
  • Build multi-agent systems capable of autonomous reasoning, planning, task delegation, and collaboration across cybersecurity functions.
  • Implement agent-to-agent coordination strategies, including shared memory, messaging, goal decomposition, and tool-use patterns.
  • Design and optimize Agent Development Kit (ADK)–based pipelines for secure, scalable agent deployment.
• RAG Systems & Knowledge Integration
  • Develop Retrieval-Augmented Generation (RAG) pipelines enabling agents to interact with real-time knowledge sources, logs, cybersecurity datasets, and enterprise APIs.
  • Optimize vector embeddings, indexing strategies, and memory structures for high-accuracy decision support.
  • Ensure grounded, auditable, and explainable outputs from LLM-based agents.
• LLM Engineering & Advanced Reasoning
  • Fine-tune, prompt-engineer, and configure LLMs/SLMs for specialized cybersecurity and automation tasks.
  • Build reasoning, planning, and self-critique modules for agents to operate autonomously and safely.
  • Integrate external LLM APIs, embeddings, synthetic data, and custom model endpoints.
• Enterprise Agentic AI Platform
  • Lead the development of an enterprise-grade platform enabling orchestration of LLMs, RAG components, vector databases, and multi-agent protocols.
  • Standardize the use of Model Context Protocol (MCP) for consistent context-sharing, memory management, and interoperability across agents.
  • Build reusable agent templates, toolkits, and internal libraries to accelerate development across Cyber teams.
• MLOps, Observability & Automation
  • Implement CI/CD, pipeline orchestration, versioning, and agent lifecycle management.
  • Establish monitoring, tracing, and observability practices for autonomous system behavior.
  • Automate manual cybersecurity processes through AI-driven workflow orchestration and dynamic agents.
• Data Engineering & Cyber Analytics
  • Extract, transform, and aggregate data from disparate cybersecurity sources such as SIEM, IAM, SOAR, endpoint telemetry, and API-driven security tools.
  • Apply ML and statistical modeling techniques for anomaly detection, classification, optimization, and pattern recognition.
  • Translate complex findings into intuitive visualizations and actionable insights for leadership.
• Cross-Functional Collaboration
  • Work with cybersecurity SMEs, analysts, and engineers to identify opportunities for autonomous decision systems.
  • Communicate complex AI concepts clearly to technical and non-technical audiences.
  • Drive innovation and advocate for emerging AI technologies across the organization.

Qualifications

Required Skills

• 5+ years total experience in software development, AI/ML engineering, or data science.
• 1+ year of Cybersecurity domain exposure, especially IAM (SailPoint, CyberArk) and SIEM/SOAR (Splunk, QRadar, etc.).
• 1+ year of hands-on experience building agentic AI or multi-agent applications, including LLM-driven workflows or reasoning systems.
• Strong Python skills and working knowledge of SQL.
• Direct experience with LLM/SLM APIs, embeddings, vector databases, RAG architecture, and memory systems.
• Experience deploying AI workloads on GCP (Vertex AI) and IBM WatsonX.
• Familiarity with agentic AI protocols, ADKs, LangGraph, AutoGen, or similar orchestration tools.
• Practical experience implementing Model Context Protocol (MCP) for agent-level context management.
• 1+ year experience with LangChain, LlamaIndex, OpenAI, Cohere, Anthropic, or similar frameworks.

Preferred

• 2+ years developing automation or RPA solutions.
• 2+ years building on AWS, including serverless architectures.
• Demonstrated experience with data visualization platforms (Tableau, Power BI, Looker).
• 2+ years working with APIs, microservices, and modern data engineering tooling.
• Applied experience with agile software development practices.
• Prior work deploying enterprise-scale agentic AI or autonomous reasoning systems.
• Contributions to open-source AI/ML or agentic frameworks.