Distinguished Engineer- AI Agentics Engineering

At CVS Health, we’re building a world of health around every consumer and surrounding ourselves with dedicated colleagues who are passionate about transforming health care. As the nation’s leading health solutions company, we reach millions of Americans through our local presence, digital channels and more than 300,000 purpose‑driven colleagues—caring for people where, when and how they choose in a way that is uniquely more connected, more convenient and more compassionate.

We do it all with heart, every day.

CVS Health is recruiting for a Distinguished Engineer – AI Agentic Engineering. In this high‑impact role, you will lead the architecture, design, and implementation of cutting‑edge autonomous AI agent systems that power intelligent automation across our enterprise operations. You will serve as a thought leader and mentor for AI engineering teams, ensuring our agentic strategy is robust, innovative and aligned with evolving business objectives.

• Strategic Agentic Architecture & Design
  • Drive the end‑to‑end architecture for highly scalable, multi‑agent systems that can operate autonomously across complex enterprise workflows.
  • Partner with other Principal Engineers, AI Architects and executive leadership to shape the long‑term agentic roadmap.
  • Champion best practices for agent reliability, interpretability, safety and performance optimization across all deployment environments.
• Agent Platform Development & Orchestration
  • Oversee the design and development of new AI agent platforms from the ground up.
  • Implement robust agent lifecycle management, including spawning, monitoring, termination and inter‑agent communication protocols.
  • Foster an engineering culture that values agent autonomy, emergent intelligence and continuous learning capabilities.
• Multi‑Agent Systems & Emerging AI Technologies
  • Provide thought leadership on how multi‑agent systems, large language models and reinforcement learning create unique demands on infrastructure.
  • Understand how to move AI agents from proof‑of‑concept to production‑ready autonomous systems.
  • Evaluate and recommend emerging agentic technologies and guide their integration into the broader technology stack.
• Cross‑Functional Leadership & AI Mentoring
  • Serve as a key technical advisor for C‑level executives and product leaders.
  • Mentor and coach senior AI engineers, data scientists and operational teams.
  • Cultivate a strong, collaborative culture across distributed teams.
• Enterprise AI Governance & Safety
  • Ensure adherence to AI ethics standards and responsible AI practices.
  • Guide compliance with internal governance frameworks for AI explainability, bias mitigation and autonomous system accountability.
  • Identify risks in autonomous agent behavior and propose mitigation strategies.

• 15+ years of Software Engineering experience.
• 7+ years in AI/ML engineering with 3+ years specifically in agentic AI or autonomous systems.
• Proven experience building multi‑agent systems from scratch.

Deep expertise in:

• Multi‑agent system architectures
  : actor model frameworks, distributed consensus protocols, agent communication standards (FIPA‑ACL, KQML, MCP, A2A) and coordination patterns.
• LLM Integration Platforms
  :
  OpenAI API, Anthropic Claude API, Azure OpenAI Service, Google Vertex AI and on‑premises LLM deployment.
• Agentic Frameworks
  :
  Lang Chain, Lang Graph, Auto Gen, CrewAI, Semantic Kernel and custom agent runtime environments.
• Tool‑using AI Systems
  : function calling implementations, API integration patterns, IDEs, notebooks, tool selection algorithms and sandbox execution environments.
• Agent Orchestration Platforms
  :
  Kubernetes‑based agent deployment, Apache Airflow, Temporal, Agentspace and event‑driven architectures (Kafka, Rabbit
  
  MQ).
• Vector Databases & Knowledge Systems
  :
  Pinecone, Weaviate, Chroma, Qdrant and knowledge graph technologies.
• Real‑time Inference Infrastructure
  : NVIDIA Triton Inference Server, Ray Serve, Torch Serve and streaming architectures.
• Planning & Reasoning Engines
  : PDDL planners, Monte Carlo Tree Search, ReAct patterns, chain‑of‑thought implementations and multi‑step reasoning frameworks.
• Agent Monitoring & Observability
  :
  Lang Smith, Weights & Biases…