Service Delivery Center, AI&D, AI Engineer - Senior - Tampa

At EY, we're all in to shape your future with confidence.

We'll help you succeed in a globally connected powerhouse of diverse teams and take your career wherever you want it to go.  Join EY and help to build a better working world.

EY is the only professional services firm with a separate business unit ("FSO") that is dedicated to the financial services marketplace. Our FSO teams have been at the forefront of every event that has reshaped and redefined the financial services industry. This practice also has several Service Delivery Centers that are made up of high-performing US-based resources who work closely with our experienced client-serving professionals to deliver project-based work and managed services to our US-based Financial Services clients.

If you have a passion for rallying together to solve the most complex challenges in the financial services industry, come join our dynamic FSO team!

** The Opportunity*
* Data has yet to be utilized to its fullest potential. Financial institutions are looking to build smarter and more efficient ways to operate their business, through new opportunities uncovered by their data. You'll be solving complex problems, as well as giving deliverables to our clients in the AI and data space. With support from a highly talented team, you'll have tremendous growth opportunities, with a focus on continuous learning and skills development to become a leader that can make significant contributions to companies.

*
* Key Responsibilities:

*
* This role contributes to the design, development, and testing of AI agents and multi-agent systems, supporting scalability, security, and observability in LLM and RAG solutions. It requires hands-on experience with agentic frameworks, prompt engineering, evaluation pipelines, and safety testing, preferably with Google-ADK, Lang Chain/Lang Graph, and vector databases. Candidates must have a bachelor's or master's degree, 8+ years of software engineering experience, and a proven record of delivering AI/ML projects.

+ Participate in the development and testing of AI agents and multi-agent systems.

+ Support state and memory management, evaluation, and orchestration in agentic solutions.

+ Assist in designing systems for human oversight and feedback to improve agent performance.

+ Contribute to explainable AI frameworks for transparent model decisions.

+ Help implement scalable and secure LLM systems with observability features.

+ Support observability (tracing, logging, evaluation) and CI/CD evaluation gates for AI agents.

+ Integrate LLMs into systems, apply prompt engineering, and assist in fine-tuning models.

+ Contribute to Retrieval-Augmented Generation (RAG) systems, including vector databases and embeddings.

+ Assist in designing test suites and human-in-the-loop review processes for AI systems.

+ Support the definition and automation of agent behavior metrics.

+ Help implement evaluation pipelines and analyze agent internal processes.

+ Participate in safety and adversarial testing, including prompt injection and jail breaking.

+ Support RAG component testing for contextual precision and document quality.

*
* Qualifications:

*
* + Bachelor's or master's degree in Computer Science, Engineering, Mathematics, or a related field.

+ 5+ years of experience in software engineering, with at least 3+ year focused on AI/ML solution development.

+ Experience delivering AI/ML projects in production environments.

+ Good communication and teamwork skills.

** Technical

Skills:

*
* + Agentic AI Architecture:

Experience with multi-agent systems, state/memory management, and explainable AI.

+ Agentic Frameworks:
Exposure to Google-ADK and Lang Chain/Lang Graph.

+ MLOps/AIOps:
Understanding of scalable LLM systems, observability, and CI/CD evaluation gates.

+ LLMs:
Integration, prompt engineering (zero-shot, few-shot, chain-of-thought), and model fine-tuning.

+ RAG Systems:
Familiarity with vector databases (Pinecone, Weaviate, PGVector), embeddings, and knowledge graphs.

+ Test Strategy:
Test suite design for AI, golden datasets, and human-in-the-loop review.

+ Agent Metrics:
Task completion, tool-use success, and error recovery.

+ Evaluation:
Evaluation pipelines and…