AI Engineer/Architect

Lead the design and delivery of enterprise agentic Generative AI capabilities for a Health Care client in a hybrid role based in Lafayette, LA.

Responsibilities

• Own architecture and technical direction for enterprise agentic AI solutions, with a balance of hands-on engineering and design governance
• Establish reusable patterns for multi-agent orchestration, MCP-enabled tool ecosystems, secure backend services, integration, observability, and production reliability
• Architect and implement robust multi-agent orchestration using Python and LangGraph, including routing, dynamic handoffs, shared state management, long term memory, tool calling, error recovery, and follow-up conversation flows
• Define target and reference architectures for agentic AI, retrieval augmented generation (RAG), model access, memory, evaluation, and human-in-the-loop controls
• Create reusable architecture patterns, engineering standards, guardrails, and design review practices for enterprise AI solutions
• Design, develop, and maintain MCP servers using FastAPI and Python to expose tools, resources, prompts, and custom capabilities within the agent ecosystem
• Define standards for tool contracts, discovery, versioning, permissions, schema validation, error handling, and safe execution
• Build and maintain custom tools and integrations connecting AI agents to internal APIs, enterprise data sources, and legacy systems
• Design AI-powered chatbots and insights engines for healthcare and pharmacy benefit management workflows, including claims, pharmacy search, drug coverage, and prior authorization
• Translate business and product requirements into scalable technical designs; guide solutions from proof of concept through production implementation
• Select appropriate model, RAG, memory, orchestration, and tool use patterns based on quality, latency, cost, security, and compliance
• Own architecture and development of high-performance FastAPI services, including streaming responses, asynchronous processing, custom middleware, rate limiting, and authentication and authorization strategies
• Design resilient integration patterns for APIs and legacy platforms, including retries, idempotency, timeouts, circuit breakers, fallbacks, and auditability
• Ensure solutions follow security, privacy, responsible AI, secrets management, input/output validation, and best practices for regulated data handling
• Implement comprehensive observability using LangSmith with distributed tracing, monitoring, logging, evaluation, error handling, and performance tuning for AI agent workloads
• Define service level objectives and quality measures for latency, answer quality, tool accuracy, task completion rate, reliability, and cost
• Identify and prioritize technical improvements in agent performance, latency, tool accuracy, scalability, and overall system architecture
• Collaborate cross-functionally with frontend, DevOps, product, security, data, and enterprise architecture teams to deliver end-to-end AI capabilities with high reliability
• Lead architecture reviews, mentor developers, communicate design trade-offs, and provide implementation guidance for distributed delivery teams
• Evaluate emerging AI technologies pragmatically and recommend adoption based on measurable business value and enterprise readiness
• Own end-to-end solution architecture from discovery and design through implementation, production readiness, and adoption
• Drive architectural simplification, reuse, and consistent engineering practices across AI implementations
• Act as a hands-on technical leader validating critical designs and implementation patterns through working code and prototypes
• Build trusted partnerships across product, engineering, DevOps, security, data, and enterprise architecture teams

Requirements

• 12+ years of professional software engineering and solution architecture experience, including hands-on delivery of enterprise applications and platforms
• 5+ years of AI/ML experience with recent hands-on delivery of production Generative AI and agentic AI solutions
• Expert-level Python skills and strong experience designing scalable, secure, production-grade backend services using FastAPI
• Hands-on experience with LangGraph (or comparable) for multi-agent orchestration, including routing, handoffs, shared state, memory, tool use, recovery, and conversational continuity
• Experience designing and implementing MCP servers, including governing tools, resources, prompts, schemas, permissions, and lifecycle management
• Deep understanding of LLMs, prompt engineering, RAG, embeddings, vector search, memory patterns, function/tool calling, model evaluation, and guardrails
• Proven experience designing AI-powered chatbots, insights engines, or workflow automation integrating with enterprise APIs, data sources, and legacy systems
• Strong knowledge of API and distributed system patterns, including streaming, asynchronous processing, middleware, rate limiting, authentication, authorization, resilience, and observability
• Experience implementing LangSmith or equivalent AI observability for tracing, evaluation, debugging, and performance monitoring
• Strong understanding of cloud-native architecture, containers, CI/CD, security, privacy, responsible AI, and operational support for regulated enterprise workloads
• Demonstrated ability to lead architecture decisions, mentor engineering teams, facilitate design reviews, and communicate complex trade-offs to technical and business stakeholders

Technologies

• Python
• Large Language Models (LLMs)
• Prompt engineering
• Embeddings
• Vector databases
• Agent-based architectures
• LangGraph
• MCP servers
• FastAPI
• LangSmith
• Retrieval augmented generation (RAG)
• Vector search
• Function/tool calling

Benefits

• Competitive compensation
• Comprehensive insurance options
• Matching contributions through the 401(k) plan and the share purchase plan
• Paid time off for vacation, holidays, and sick time
• Paid parental leave
• Learning opportunities and tuition assistance
• Wellness and Wellbeing programs

Compensation: USD 80,600 - 218,200 per year.

Work model & location: Hybrid in Lafayette, LA.

Other details: This role can be performed from any Client site locations listed as Bloomfield, CT, Raleigh, NC, or Lafayette, LA under a hybrid working model. CGI may be required by law in some jurisdictions to include a reasonable estimate of the compensation range; the reasonable estimate for this role in the U.S. is $80,600.00 - $218,200.00.