Agentic AI Engineer

Overview

Job Description :

Our client is looking for an Agentic AI Engineer in Toronto, ON Must Have Primary Skills

We are seeking a highly skilled and experienced Agentic AI Engineer to join our AI Engineering team within the Financial Services division. The successful candidate will be responsible for designing, building, and deploying autonomous and semi-autonomous AI agents that automate complex, multi-step financial workflows, enhance client engagement (e.g., Robo-Advisory), and drive operational efficiency, while adhering to strict regulatory and compliance standards. This is a critical role blending expertise in Large Language Models (LLMs), software engineering, and the regulated environment of banking. Nice To Have Secondary Skills

Design, develop, and implement production-grade AI agents and multi-agent systems using modern orchestration frameworks (e.g., LangChain, LangGraph, CrewAI, or proprietary internal frameworks). Architect and optimize Retrieval-Augmented Generation (RAG) pipelines to ground agents in proprietary and secure financial data sources (e.g., CRM, transaction logs, compliance documents). Develop robust "Tool Use" capabilities, enabling agents to autonomously interact with banking systems, APIs, and microservices (e.g., for transaction monitoring, loan pre-assessment, or reporting). Implement advanced prompt engineering techniques and fine-tuning (where necessary) to guide agent behavior and ensure high-quality, reliable, and compliant outputs. Build and maintain the core platform components that facilitate the secure and scalable deployment of AI agents on cloud infrastructure (e.g., Azure, AWS) using containerization (Docker, Kubernetes). Embed Responsible AI (RAI) principles, including safety, guardrails, bias detection, and explainability (XAI) directly into agent logic and platform services, ensuring alignment with financial industry regulations. Develop comprehensive testing and evaluation harnesses (using frameworks like LangSmith or Langfuse) to measure agent performance (e.g., task success rate, hallucination rate, F1 score) before and after production release. Ensure all agents comply with internal risk frameworks, AML (Anti-Money Laundering), KYC (Know Your Customer), and other relevant financial regulatory requirements. Partner closely with Data Scientists, Quantitative Analysts, Product Managers, and Compliance teams to identify high-impact use cases (e.g., fraud detection, compliance monitoring, credit scoring). Provide technical guidance and evangelize best practices for agentic design and LLM usage across the engineering organization. Stay current with advancements in agentic AI, multi-modal LLMs, and Generative AI research, proposing and prototyping new solutions. Proven Experience In

Qualifications Experience:

3+ years of experience in AI/ML engineering, software development, or a related quantitative field, with 1+ years focused specifically on developing and deploying Generative AI or Agentic systems. Technical Expertise (Must-Have): Expert proficiency in Python and developing enterprise-grade, clean, and modular code. Hands-on experience with at least one major LLM orchestration framework (e.g., LangChain, LangGraph). Proficiency with cloud platforms (Azure, AWS, or GCP) and related technologies (Docker, Kubernetes). Strong understanding of MLOps principles, CI/CD pipelines, and robust system observability (logging, metrics, tracing). Domain Knowledge: Previous experience working within the financial services, wealth management, or other highly regulated industries is strongly preferred. IND1

Email: relangovan@finney-taylor.com Industry experience required: Banking

#J-18808-Ljbffr