Principal Engineer, Agentic AI

Job Description Summary

This role is at the leading edge of Raymond James’ AI evolution—building systems that convert the firm’s collective intelligence into secure, adaptive knowledge that serves clients better every day.
This role is at the leading edge of Raymond James’ AI evolution—building systems that convert the firm’s collective intelligence into secure, adaptive knowledge that serves clients better every day.
It’s demanding work—technically complex, mission-critical, and transformative—but it’s work that matters. You’ll have the opportunity to shape the systems that define how knowledge flows, how teams collaborate, and how the firm competes at the top of the industry for years to come.

Job Description

Responsibilities

Raymond James is pioneering a new class of agentic AI systems—intelligent, adaptive platforms that continuously learn from firm knowledge and act responsibly to enhance decision-making and client outcomes. These systems will enable real-time knowledge orchestration and insight generation across the enterprise, amplifying the collective intelligence of our advisors, associates, and business units.

As part of the Agentic AI Data Science team, you will architect and deliver scalable, secure, and high-performance agentic solutions using and extending frameworks such as Strands, CrewAI, LangGraph, Agent Core, and related technologies. You will help design the foundational infrastructure that allows these systems to learn safely, adapt in real time, and deliver measurable value—all while operating within the disciplined, client-first culture that defines Raymond James.

This is a hands-on engineering role requiring exceptional technical depth, strong design judgment, and a passion for building systems that are both innovative and enduring. You’ll collaborate across engineering, data, and governance teams to ensure every solution balances speed, integrity, and long-term impact.

A good understanding of scalable, reliable, and reusable Agent Harnesses.

Architect and Build Agentic Systems: Design and implement agentic AI architectures capable of reasoning, planning, and self-adaptation within firm-approved security and compliance boundaries.

• Leverage and Extend Frameworks: Utilize and enhance frameworks such as Strands, CrewAI, LangGraph, and Agent Core to create standardized, reusable components that accelerate agentic development across teams.

• Cloud Engineering: Develop secure, resilient, and scalable cloud-native solutions using AWS services (Lambda, ECS, S3, API Gateway, SageMaker, Bedrock, etc.) to support production-grade AI operations.

• Monitoring and Evaluation: Implement metrics, tracing, and evaluation pipelines that ensure transparency, reliability, and continuous improvement in agentic behavior.

• Integration and Governance: Collaborate with security, risk, and compliance to embed governance, auditability, and ethical safeguards into all systems.

• Collaboration: Partner with data science, enterprise architecture, and application engineering teams to integrate agentic capabilities into firm platforms. Innovation Leadership: Research, test, and recommend new frameworks and patterns that responsibly advance the firm’s AI capabilities.

• Ownership: Drive full lifecycle delivery—from technical design through deployment and iteration—maintaining high standards of reliability and documentation.

• Other responsibilities as assigned.

Skills

• Proficiency in Python (with experience in TypeScript, Go, or Java a plus).

• Solid understanding of AWS architecture and services—deployment, monitoring, security, and cost optimization.

• Required experience in agentic or LLM frameworks such as Strands, CrewAI, LangGraph, Agent Core, or similar.

• Experience with retrieval systems, vector databases, embeddings, and orchestration frameworks.

• Strong grounding in secure API design, data modeling, and CI/CD automation.

• - Proven record of writing clean, testable, production-grade code.

• Experience designing tool/function-calling integrations and Model Context Protocol (MCP) servers and connectors.

• Strong prompt and context engineering, including agent memory, state, and session/context management.

• Experience with agent and LLM evaluation, guardrails, and safety controls—hallucination mitigation, content filtering, and human-in-the-loop oversight.

• Hands-on experience with foundation models via Amazon Bedrock (e.g., Anthropic Claude), including model selection and prompt/parameter tuning for latency and cost.

• Familiarity with multi-agent orchestration and workflow design—planning, task decomposition, routing, tool use, and error handling.

• Experience with containerization and orchestration (Docker, Kubernetes) for deploying scalable, resilient services.

• Knowledge of Terraform for IaC deployments. Hands-on experience with Terraform is a plus.

• OpenTelemetry for Dynatrace and Observability

• Experience with agent performance tuning and cost optimization.

• Experience with time-boxed A2A and Swarm/Crew Agentic solutions

• Deploying large language models on-prem

• Experience with fine-tuning LLMs - nice to have

• Mindset: Deep curiosity, bias toward execution, and respect for precision and reliability.

• Financial services experience preferred but not required.

Education

Bachelor’s: Computer and Information Science, Bachelor’s (Required)

Work Experience

General Experience – 10 to 15 years

Certifications

Travel

Less than 25%

Workstyle

Hybrid

The total compensation for this position includes base salary or wages, and may include components such as additional compensation (cash or equity), discretionary bonuses, or commissions. This position is eligible for a benefits package that may include medical, dental, and vision; life insurance; critical illness insurance and accident insurance; disability benefits; retirement savings; paid time off (including vacation, holidays, and sick leave); and parental leave.  Eligibility for benefits and specific offerings may vary based on position and employment status. To view more details of the benefits offered, visit Myrjbenefits.com.

At Raymond James our associates use five guiding behaviors (Develop, Collaborate, Decide, Deliver, Improve) to deliver on the firm's core values of client-first, integrity, independence and a conservative, long-term view. 
We expect our associates at all levels to:
•  Grow professionally and inspire others to do the same
•  Work with and through others to achieve desired outcomes
•  Make prompt, pragmatic choices and act with the client in mind
•  Take ownership and hold themselves and others accountable for delivering results that matter
•  Contribute to the continuous evolution of the firm

At Raymond James – as part of our people-first culture, we honor, value, and respect the uniqueness, experiences, and backgrounds of all of our Associates.  When associates bring their best authentic selves, our organization, clients, and communities thrive. The Company is an equal opportunity employer and makes all employment decisions on the basis of merit and business needs. 

#LI-SA1