Agentic AI Engineer - Anthropic/Claude

Summary

Deloitte is growing its AI & Engineering team to help organizations build and scale responsible technology solutions. The AI and Data Science Engineer II will design and deliver Generative AI and agentic solutions powered by Anthropic Claude, lead technical workstreams, and support client engagements from solution design through production rollout.

Responsibilities

• Engage with client stakeholders and sponsors, acting as the primary technical point of contact for your workstream
• Design and build Generative AI and agentic solutions using Claude, including agent orchestration, tool integration, and Model Context Protocol (MCP) based integrations, using the Claude Agent SDK and Claude Cowork
• Deliver components of client engagements spanning solution design, prototyping, testing, and production rollout
• Lead small teams through business requirements gathering, functional design, process mapping, and support-model definition, providing technical direction throughout
• Monitor progress against plan, identify variances, and drive corrective action before issues affect delivery
• Identify risks, assumptions, and constraints early, and implement approved mitigations to protect delivery
• Maintain clear, consistent communication with client stakeholders and internal engagement leadership
• Designing and building agentic AI solutions powered by Claude, from proof-of-concept through production deployment
• Implementing multi-agent systems that automate business processes, integrate with enterprise tools, and operate within defined autonomy and guardrails
• Modernizing existing AI/ML or data platforms to incorporate Generative AI capabilities, including retrieval-augmented generation and agent-based orchestration
• Advising clients on Generative AI adoption strategy, responsible AI practices, and model/platform selection
• Partnering directly with client technology, data, and business stakeholders to scope and deliver AI solutions

Skills

• Ability to work independently and collaborate as part of a team
• Effective written and verbal communication skills
• Meticulous attention to detail and quality of work product
• Ability to build and sustain professional relationships
• Ability to lead projects or workstreams
• Ability to manage and prioritize multiple tasks in a fast-paced and dynamic environment
• Strong interpersonal skills and professional demeanor
• Ability to meet deadlines
• Ability to provide clear guidance to others
• 3+ years of experience designing, developing, and delivering AI/ML solutions
• 2+ years of hands-on experience developing AI/ML applications in Python
• At least 1 year of direct experience designing or implementing production agentic workflows involving capabilities such as orchestration, tool integration, state management, evaluation, guardrails, and human-in-the-loop controls
• At least six months of hands-on experience developing agentic AI solutions using the Claude Agent SDK, including agent orchestration, tool integration, permissions, or MCP integrations
• At least six months of hands-on experience developing and deploying production solutions using Anthropic Claude models through the native Anthropic API or a supported cloud platform
• At least six months of experience applying prompt engineering, context engineering, structured outputs, and related techniques to improve the performance, reliability, and usability of AI solutions
• 1+ years of experience leading project workstreams or engagements
• Bachelor's or Master's degree in Computer Science, Engineering, Data Science, AI, or a related field
• Limited immigration sponsorship may be available
• Experience in consulting or other client-facing delivery roles
• Experience using Claude Cowork to support enterprise workflows, automation, research, or other knowledge-work use cases
• Hands-on experience using Claude through one or more of the following: Azure AI Foundry, Amazon Bedrock, Google Vertex AI, or the native Anthropic API
• Experience with multi-agent systems, MCP integrations, agent evaluation, observability, safety controls, or production governance
• Certifications such as Claude Certified Architect - Professional (CCAR-P), Claude Certified Architect - Foundations (CCAR-F), or Claude Certified Developer - Foundations (CCDV-F)
• Cloud certification(s) - AWS, Azure, or Google Cloud
• Experience creating client workshop collateral and leading interactive working sessions
• Experience presenting technical content to both large and small audiences

Qualifications

Must Haves

• Ability to work independently and collaborate as part of a team
• Effective written and verbal communication skills
• Meticulous attention to detail and quality of work product
• Ability to build and sustain professional relationships
• Ability to lead projects or workstreams
• Ability to manage and prioritize multiple tasks in a fast-paced and dynamic environment
• Strong interpersonal skills and professional demeanor
• Ability to meet deadlines
• Ability to provide clear guidance to others
• 3+ years of experience designing, developing, and delivering AI/ML solutions
• 2+ years of hands-on experience developing AI/ML applications in Python
• At least 1 year of direct experience designing or implementing production agentic workflows involving capabilities such as orchestration, tool integration, state management, evaluation, guardrails, and human-in-the-loop controls
• At least six months of hands-on experience developing agentic AI solutions using the Claude Agent SDK, including agent orchestration, tool integration, permissions, or MCP integrations
• At least six months of hands-on experience developing and deploying production solutions using Anthropic Claude models through the native Anthropic API or a supported cloud platform
• At least six months of experience applying prompt engineering, context engineering, structured outputs, and related techniques to improve the performance, reliability, and usability of AI solutions
• 1+ years of experience leading project workstreams or engagements
• Bachelor's or Master's degree in Computer Science, Engineering, Data Science, AI, or a related field
• Limited immigration sponsorship may be available

Nice to Haves

• Experience in consulting or other client-facing delivery roles
• Experience using Claude Cowork to support enterprise workflows, automation, research, or other knowledge-work use cases
• Hands-on experience using Claude through one or more of the following: Azure AI Foundry, Amazon Bedrock, Google Vertex AI, or the native Anthropic API
• Experience with multi-agent systems, MCP integrations, agent evaluation, observability, safety controls, or production governance
• Certifications such as Claude Certified Architect - Professional (CCAR-P), Claude Certified Architect - Foundations (CCAR-F), or Claude Certified Developer - Foundations (CCDV-F)
• Cloud certification(s) - AWS, Azure, or Google Cloud
• Experience creating client workshop collateral and leading interactive working sessions
• Experience presenting technical content to both large and small audiences

Benefits

• You may also be eligible to participate in a discretionary annual incentive program, subject to the rules governing the program, whereby an award, if any, depends on various factors, including, without limitation, individual and organizational performance.