Senior AI Engineer – Cyber Architecture, OT and Engineering

This is a fully remote position, open to applicants in India.

📋 Description

• Design, architect, and implement agentic AI workflows utilizing frameworks such as LangChain, LangGraph, AutoGen, and other orchestration libraries.

• Create multi-agent systems that are capable of autonomous reasoning, planning, task delegation, and collaboration within cybersecurity domains.

• Execute agent-to-agent coordination techniques, incorporating shared memory, messaging, goal decomposition, and patterns for tool usage.

• Develop and enhance pipelines based on the Agent Development Kit (ADK) for secure and scalable deployment of agents.

• Construct Retrieval-Augmented Generation (RAG) pipelines that allow agents to engage with real-time knowledge sources, logs, cybersecurity datasets, and enterprise APIs.

• Refine vector embeddings, indexing methods, and memory structures to ensure high-accuracy decision-making support.

• Guarantee that outputs from LLM-based agents are grounded, auditable, and explainable.

• Fine-tune, prompt-engineer, and set up LLMs/SLMs for specific cybersecurity and automation functions.

• Develop reasoning, planning, and self-critique components that enable agents to function autonomously and safely.

• Integrate external LLM APIs, embeddings, synthetic data, and customized model endpoints.

⛳️ Requirements

• Over 5 years of overall experience in software development, AI/ML engineering, or data science.

• At least 1 year of experience in the Cybersecurity field, particularly in IAM (SailPoint, CyberArk) and SIEM/SOAR (Splunk, QRadar, etc.).

• A minimum of 1 year of practical experience in developing agentic AI or multi-agent systems, including LLM-driven workflows or reasoning mechanisms.

• Proficient in Python and possess a working knowledge of SQL.

• Direct experience with LLM/SLM APIs, embeddings, vector databases, RAG architecture, and memory systems.

• Experience in deploying AI workloads on GCP (Vertex AI) and IBM WatsonX.

• Familiar with agentic AI protocols, ADKs, LangGraph, AutoGen, or similar orchestration tools.

• Hands-on experience in implementing the Model Context Protocol (MCP) for managing agent-level context.

• More than 1 year of experience with LangChain, LlamaIndex, OpenAI, Cohere, Anthropic, or similar frameworks.

🏝️ Benefits

• Health insurance

• Flexible work arrangements

• Professional development opportunities