Agentic AI Developer - Senior Consultant

Company Description At Deloitte , our Purpose is to make an impact that matters for our clients, our people, and society.

Minimum Requirements

• Bachelor’s degree in Computer Science, Engineering, Mathematics, Statistics, Data Science or Physics .
• Minimum 3 years of relevant professional experience in software engineering, AI, or advanced data systems.
• Demonstrable interest in Generative AI and Agentic AI , evidenced through: Courses or certifications
• Practical projects or implementations
• Research, reading, or published materials
• Experience in financial risk, regulatory risk, or compliance-driven environments .
• Exposure to regulatory, audit‑driven, or high‑governance technology contexts .
• AI, Generative AI, or cloud architecture certifications.
• Engineers who understand that Agentic AI is not just prompt engineering , but systems design.
• Builders who are comfortable working in regulated, audit-sensitive environments .
• Professionals who can balance innovation with control , autonomy with accountability.
• Individuals motivated to move agentic concepts into production‑grade, defensible solutions .

Responsibilities

• Design and implement agent-based architectures , defining how agents: Gather and reason over context
• Plan and make decisions
• Coordinate with other agents
• Interact safely with tools, APIs, and enterprise systems
• Build and maintain robust agent runtime environments that support cognition, orchestration, and execution at scale.
• Implement reasoning and control frameworks (e.g. planning, reflection loops, evaluation pipelines) to enable safe, traceable, and reliable agent behaviour.
• Develop using modern Agentic AI frameworks and orchestration tools , such as: LangGraph
• Langflow
• N8N
• LangChain
• Apply knowledge of agent communication and orchestration protocols (e.g. MCP, ACP, A2A, ANP) where appropriate.
• Design and implement security, observability, and governance controls aligned to regulated or high‑risk environments.
• Establish guardrails to ensure alignment, safety, and reliability for semi‑autonomous or autonomous operations.
• Monitor, evaluate, debug, and continuously improve agent performance using telemetry, evaluation signals, and feedback loops.
• Design human‑in‑the‑loop and human‑on‑the‑loop workflows that ensure AI augments business capability, whilst minimising operational or regulatory risk.
• Optimise user interactions and hand‑offs between operational teams and agentic systems.
• Strong programming capability with Python (required).
• Experience building, testing, and deploying LLM‑based or agentic systems in real-world environments.
• Solid understanding of software architecture, APIs, and distributed systems .
• Experience with some or all of the following: Python, ASP.NET Core, Entity Framework
• Angular or React
• PostgreSQL or similar relational databases
• MongoDB or similar document databases
• Git
• Experience with virtualisation and containerisation platforms, e.g Docker, Kubernetes.
• Azure AI Foundry / Amazon Bedrock Experience
• General cloud experience with AWS, Azure and/or GCP .
• Cloud architecture and/or AI-related certifications are advantageous.