Agentic AI Developer

About the role

This is an exciting opportunity to work in a fast-paced team environment supporting one of the largest leaders in the Health Care industry. This Senior AI Engineer will be instrumental to design, develop, and lead enterprise-grade Generative AI solutions.

Responsibilities

• Technical Leadership & Architecture
  • Lead the design and development of scalable Generative AI solutions using LLMs
  • Define and implement architectures for RAG, agentic, multi-agent, and multimodal systems
  • Review and guide solution designs to ensure alignment with AI CoE standards and enterprise architecture
  • Mentor and guide developers on GenAI patterns, tools, and best practices
• Development & Engineering
  • Develop end-to-end AI solutions using Python
  • Design, test, and optimize prompt engineering strategies
  • Build and manage embeddings, vector search, and semantic retrieval pipelines
  • Develop applications using LangChain and monitor, evaluate, and debug workflows using LangSmith
  • Integrate LLMs with enterprise systems, APIs, and structured/unstructured data sources
  • Implement agent-based and multi-agent workflows for task orchestration and automation
  • Work with multimodal models involving text, documents, and images
• Collaboration with AI CoE
  • Work closely with the AI CoE to align on AI frameworks, reusable components, and architectural standards
  • Contribute to enterprise GenAI accelerators, reference architectures, and best practices
  • Support governance, security, responsible AI, and compliance requirements
  • Share learnings, patterns, and improvements across teams to drive consistency and adoption
• AI & LLM Expertise
  • Apply deep understanding of LLM capabilities, limitations, and optimization techniques
  • Evaluate and recommend appropriate models (OpenAI, Azure OpenAI, open-source)
  • Ensure performance, scalability, cost optimization, and reliability of AI solutions

Requirements

• At least 5+ years of professional software engineering experience, with strong hands-on expertise in Python or Java building scalable, production-grade applications.
• 2+ years in LangChain, LangGraph, LangSmith, prompt engineering, multi LLM/model orchestration, tool calling, RAG, evaluation, and deployment.
• Strong experience developing GenAI applications using LangChain and implementing observability, evaluation, and debugging using LangSmith or equivalent tools.
• Demonstrated experience delivering enterprise Generative AI solutions, including design and implementation of RAG, agentic, and multi-agent architectures.
• Proven hands-on experience with LLMs, including prompt engineering, optimization, evaluation, and lifecycle management in production environments.
• Experience designing and managing embeddings and vector-based retrieval pipelines using industry-standard vector databases or search platforms.
• Experience integrating GenAI solutions with enterprise platforms, APIs, and data sources, including structured data, documents, and unstructured content.
• Hands-on experience implementing tool/function calling, memory, and agent orchestration to support complex workflows and automation use cases.
• Experience working with multimodal AI solutions involving text, documents, and images.
• Proven ability to evaluate, select, and operationalize LLMs (e.g., OpenAI, Azure OpenAI, open-source) with a focus on performance, scalability, cost, and reliability.
• Experience collaborating with an AI Center of Excellence (AI CoE) to align on enterprise standards, reference architectures, and reusable components.
• Strong understanding of AI governance, security, responsible AI, and compliance requirements in regulated enterprise environments.
• Proven ability to evaluate, select, and operationalize LLMs (e.g., OpenAI, Azure OpenAI, open-source) with a focus on performance, scalability, cost, and reliability.
• Experience leading and mentoring engineering teams, reviewing designs, and establishing repeatable patterns and best practices.

Qualifications

• Required Qualifications:
  • Bachelor's degree in computer science or related field.
  • At least 5+ years of professional software engineering experience, with strong hands-on expertise in Python or Java building scalable, production-grade applications.
  • 2+ years in LangChain, LangGraph, LangSmith, prompt engineering, multi LLM/model orchestration, tool calling, RAG, evaluation, and deployment.
  • Strong experience developing GenAI applications using LangChain and implementing observability, evaluation, and debugging using LangSmith or equivalent tools.
  • Demonstrated experience delivering enterprise Generative AI solutions, including design and implementation of RAG, agentic, and multi-agent architectures.
  • Proven hands-on experience with LLMs, including prompt engineering, optimization, evaluation, and lifecycle management in production environments.
  • Experience designing and managing embeddings and vector-based retrieval pipelines using industry-standard vector databases or search platforms.
  • Experience integrating GenAI solutions with enterprise platforms, APIs, and data sources, including structured data, documents, and unstructured content.
  • Hands-on experience implementing tool/function calling, memory, and agent orchestration to support complex workflows and automation use cases.
  • Experience working with multimodal AI solutions involving text, documents, and images.
  • Proven ability to evaluate, select, and operationalize LLMs (e.g., OpenAI, Azure OpenAI, open-source) with a focus on performance, scalability, cost, and reliability.
  • Experience collaborating with an AI Center of Excellence (AI CoE) to align on enterprise standards, reference architectures, and reusable components.
  • Strong understanding of AI governance, security, responsible AI, and compliance requirements in regulated enterprise environments.
  • Proven ability to evaluate, select, and operationalize LLMs (e.g., OpenAI, Azure OpenAI, open-source) with a focus on performance, scalability, cost, and reliability.
  • Experience leading and mentoring engineering teams, reviewing designs, and establishing repeatable patterns and best practices.

Skills

• Python
• LangChain
• LangGraph
• LangSmith
• Prompt engineering
• Multi LLM/model orchestration
• Tool calling
• RAG
• Evaluation
• Deployment

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 Well-being programs

Pay

To support the ability to reward for merit-based performance, CGI typically does not hire individuals at or near the top of the range for their role. Compensation decisions are dependent on the facts and circumstances of each case. A reasonable estimate of the current range for this role in the U.S. is $80,600 - $194,000.00.

Schedule

This role can be performed from any Client site Bloomfield, CT, Raleigh, NC or Lafayette, LA in a Hybrid working Model.