Description
Summary About the Role We are looking for a skilled Agentic AI Engineer to design, build, and deploy multi-agent AI systems that power Viranetra's core intelligence layer — from real-time threat detection to autonomous investigation and response workflows. You'll work at the intersection of GenAI engineering, cloud infrastructure, and cybersecurity, turning LLM-based agents into production-grade, low-latency security systems. Key Responsibilities • Design, build, and orchestrate multi-agent AI workflows (LangChain / LangGraph) for autonomous threat detection, triage, and response • Develop and optimize RAG pipelines and context-aware memory systems for security intelligence use cases • Architect and deploy cloud-native GenAI infrastructure on AWS (EC2, Lambda, SageMaker, EKS) • Build low-latency LLM inference pipelines to meet real-time SOC performance requirements • Implement ML monitoring, agent observability, and tracing (LangSmith) for production reliability • Own end-to-end infrastructure provisioning, CI/CD, and automation for AI services (Jenkins, Docker, Kubernetes, Terraform) • Ensure secure AI deployment practices aligned with Viranetra's compliance posture (ISO 27001 / SOC 2) • Collaborate cross-functionally with product, security research, and engineering teams to integrate AI agents into Viranetra's modules (VIRA Cortex, Netra Scan, VIRA Forensic, Netra Respond) • Continuously improve model performance, latency, and system reliability based on production feedback