Join our dynamic team at Deloitte, where we empower organizations to build robust cybersecurity defenses and safeguard critical assets. We champion a secure, vigilant, and resilient approach to cyber risk management, enabling businesses to not only prevent and respond to threats but also to unlock new opportunities.

This role focuses on embedding cyber risk considerations into strategic development, ensuring more effective management of information and technology-related risks.

Design, develop, and deploy enterprise-grade AI solutions across Generative AI, Agentic AI, RAG/GraphRAG, and Machine Learning.

Build sophisticated LLM workflows incorporating prompt engineering, structured outputs, tool/function calling, and model routing.

Develop single- and multi-agent architectures to manage complex enterprise workflows, determining the optimal approach for agentic AI implementation.

Optimize LLM applications for performance, focusing on latency, token utilization, and inference costs while ensuring model abstraction and fallback strategies.

A strong foundation in Python, ML/LLM concepts, retrieval architectures, agent orchestration, backend engineering, cloud deployment, and AI evaluation is essential.

Demonstrated experience in building AI systems that perform reliably under real-world constraints such as latency, concurrency, security, scalability, cost, and failure recovery.

Proficiency in evaluating and selecting LLMs based on quality, latency, throughput, concurrency, context limits, and cost.

Familiarity with agentic AI principles and experience building agent workflows using frameworks like LangGraph.