AI Engineer

We are looking for a highly skilled AI Engineer to design, build, and scale next-generation Agentic AI systems for enterprise security automation. This role is ideal for engineers who have hands-on experience building multi-agent systems, AI copilots, intelligent automation platforms, and enterprise-grade LLM applications.
You will work at the intersection of AI, cloud infrastructure, security automation, and distributed systems to create production-ready AI solutions that drive real-world outcomes.
Responsibilities:
Design and build production-grade Agentic AI applications for enterprise security automation.
Develop and deploy multi-agent systems, AI assistants, chatbots, and autonomous workflows.
Build intelligent agents capable of tool usage, planning, reasoning, memory management, and workflow orchestration.
Develop and optimize enterprise RAG (Retrieval-Augmented Generation) systems using vector databases and knowledge retrieval pipelines.
Integrate external systems through Model Context Protocol (MCP) tools, APIs, and enterprise data sources.
Work with modern LLM ecosystems, including Anthropic Claude, OpenAI, and cloud-hosted foundation models.
Build scalable AI services leveraging AWS Bedrock and cloud-native architectures.
Implement AI observability, governance, security, and safety guardrails.
Collaborate closely with product, engineering, and security teams to deliver enterprise-grade AI capabilities.
Evaluate emerging AI frameworks, agent architectures, and orchestration technologies.
Requirements:
Experience building AI systems for cybersecurity use cases.
Contributions to open-source AI projects.
Experience evaluating and benchmarking LLMs and agent frameworks.
Familiarity with LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar agent orchestration frameworks.
Must-Have Skills and Experience:
8+ years of hands-on experience building GenAI applications in production.
Strong programming expertise in Python, . NET (C#), and TypeScript.
Hands-on experience building: Multi-agent systems, AI copilots, Chatbots, Tool-using agents, and AI-powered automation platforms.
Deep understanding of LLM orchestration frameworks, Prompt engineering, Agent memory and planning architectures, Function/tool calling, and Structured outputs.
Experience implementing: Enterprise RAG systems, Vector databases, Embeddings, Semantic search pipelines.
Strong experience with AWS Bedrock (strongly preferred), AWS cloud services, and Containerized deployments.
Good to Have:
Experience with Claude Agent SDK, OpenAI SDKs, or equivalent LLM provider frameworks.
Experience integrating tools via Model Context Protocol (MCP).
Knowledge of: AI security frameworks, LLM security, Prompt injection prevention, Data protection and governance, Responsible AI practices.
Experience with: Docker, Kubernetes, MongoDB, OpenSearch/Elasticsearch.
Exposure to: Cybersecurity, SOAR, SIEM, Security Operations.

Experience
8-12 yrs