Principal Engineer - AI/Agentics

• Drive the end-to-end implementation and deployment for highly scalable, multi-agent systems
• Partner with other Principal Engineers and AI Architects to contribute to the long-term agentic roadmap
• Champion best practices for agent reliability, interpretability, safety, and performance optimization
• Lead the development of new AI agent platforms from the ground up
• Implement robust agent lifecycle management
• Provide implantation leadership on how multi-agent systems, large language models, and reinforcement learning create unique demands on infrastructure
• Evaluate and recommend emerging agentic technologies
• Serve as a key proponent of Agentic programs with product leaders
• Support the broader AI community of engineers, data scientists, and operational teams
• Ensure adherence to AI ethics standards and responsible AI practices
• Support compliance with internal governance frameworks for AI explainability, bias mitigation, and autonomous system accountability
• Identify risks in autonomous agent behavior and propose mitigation strategies

• 5+ years in AI/ML engineering with 2+ 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
• Deep expertise in LLM Integration Platforms: OpenAI API, Anthropic Claude API, Azure OpenAI Service, Google Vertex AI, and on-premises LLM deployment
• Deep expertise in Agentic Frameworks: LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, and custom agent runtime environments
• Deep expertise in Tool-using AI Systems: Function calling implementations, API integration patterns, IDE, Notebooks, tool selection algorithms, and sandbox execution environments
• Deep expertise in Agent Orchestration Platforms: Kubernetes-based agent deployment, Apache Airflow for agent workflows, Temporal for durable agent executions, Agentspace, and event-driven architectures
• Deep expertise in Vector Databases & Knowledge Systems: Pinecone, Weaviate, Chroma, Qdrant for agent memory systems, and knowledge graph technologies
• Deep expertise in Real-time Inference Infrastructure: NVIDIA Triton Inference Server, Ray Serve, TorchServe, and streaming architectures
• Deep expertise in Planning & Reasoning Engines: PDDL planners, Monte Carlo Tree Search, ReAct patterns, Chain-of-Thought implementations, and multi-step reasoning frameworks
• Deep expertise in Agent Monitoring & Observability: LangSmith, Weights & Biases, custom telemetry systems, and agent behavior analytics platforms
• Deep expertise in Security & Sandboxing: Docker/containerd for agent isolation, WebAssembly runtimes, secure code execution environments, and prompt injection mitigation strategies
• Problem-solving mindset: Ability to design emergent behaviors and deliver pragmatic autonomous solutions
• Bachelor's Degree in Computer Science, Engineering, or related field

Leadership: Track record of guiding AI teams and driving cross-functional alignment in complex AI initiatives

• Affordable medical plan options
• 401(k) plan with matching company contributions
• Employee stock purchase plan
• No-cost wellness screenings
• No-cost tobacco cessation programs
• No-cost weight management programs
• Confidential counseling
• Financial coaching
• Paid time off
• Flexible work schedules
• Family leave
• Dependent care resources
• Colleague assistance programs
• Tuition assistance
• Retiree medical access