Agentic AI - Lead Application Developer

Contract Duration: 12+ Months

Location: St. Petersburg, FL (Hybrid for 3 days)

• 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, Lang Graph, 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, Sage Maker, 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

• Proficiency in Python (with experience in Type Script, Go, or Java a plus)
• Solid understanding of AWS architecture and services—deployment, monitoring, security, and cost optimization
• Familiarity with agentic or LLM frameworks such as Strands, CrewAI, Lang Graph, Agent Core, or similar
• Experience with retrieval systems, vector databases, embeddings, and orchestration framework
• 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
• A good understanding of scalable, reliable, and reusable Agent Harnesse
• Knowledge of Terraform for IaC deployments; hands‑on experience with Terraform is a plus
• Open Telemetry 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