Principal Engineer - Agentic AI (US)

TD Bank•Mount Laurel, NJ

About The Position

We are looking for a skilled Principal Agentic AI Engineer to architect, build, and deploy advanced AI agents capable of autonomous reasoning, decision-making, and self-directed execution. In this role, you will architect, develop, and optimize agentic AI systems, including autonomous agents, multi-agent frameworks, and LLM-powered agents and integrate these solutions into existing TD Bank applications. This person provides deep technical leadership, domain specialization and expertise, and sets direction in developing and implementing solutions to address emerging business needs and strategies and also advances the overall design architecture and technology capabilities in accordance with industry developments. This role is also influential to Senior Leaders and provides guidance and governance to other technology groups and business areas. Depth & Scope: Recognized as an internal and external expert in specific domain(s) within the organization; Spends the majority of their time on technical issues Sets the direction and oversees the work of other IT professionals as assigned on complex, highly-visible engineering projects of significant profile, strategic importance, and enterprise impact to the Bank Recognized as an internal expert within the broad engineering field and may have specialized expertise within multiple domains Provides consultative and strategic guidance to executive leadership

Requirements

Bachelor's or Graduate degree
Strong academic background (e.g. computer science, engineering) or 15+ years relevant experience

Nice To Haves

15+ Years experience building and delivering enterprise grade solutions at financial institutions using various different programming languages
2+ years of experience in Python for developing and deploying AI-enabled applications, such as LLMs, RAG, GraphRAG and agentic workflows
Hands-on experience with agentic AI frameworks and concepts such as LangChain, LangGraph, AutoGen, Model Context Protocol (MCP), large language models (LLMs), chain-of-thought prompting, knowledge stores, and embeddings
Expert level knowledge of prompt engineering techniques and model fine-tuning
Strong understanding of cybersecurity principles as they apply to AI systems, including threat modeling and vulnerability assessment.
Hands on with Azure OpenAI (GPT 4/4 Turbo, Assistants/On Your Data), Azure AI Search/vector indexing, embeddings, and prompt engineering; proven RAG implementations.

Responsibilities

Architect, develop, and optimize agentic AI systems, including autonomous agents, multi-agent frameworks, and LLM-powered agents
Integrate these solutions into existing TD Bank applications
Provide deep technical leadership, domain specialization and expertise
Set direction in developing and implementing solutions to address emerging business needs and strategies
Advance the overall design architecture and technology capabilities in accordance with industry developments
Provide guidance and governance to other technology groups and business areas