Lead Agentic AI Engineer

Role overview This is a hands-on technical leadership role for someone who can architect, build, and operationalize enterprise-grade autonomous AI agent systems integrated with a major CRM platform. The engineer serves as the primary authority on stateful multi-agent workflows, frontier large language models, modern orchestration engines, and the protocols that bridge complex business requirements with robust software engineering. Success in the role means embedding safe, high-accuracy, and deterministic AI agents into customer relationship management, data cloud, and core operational systems while operating inside strict transactional and enterprise data security boundaries.

Responsibilities - Architect stateful multi-agent coordination graphs using frameworks like LangGraph or custom DAG loops, supporting dynamic task decomposition, supervisor orchestration, human-in-the-loop escalation, and automated error recovery. - Build standardized Model Context Protocol (MCP) servers and connectors to securely expose CRM tools, objects, custom actions, and operational context to agent runners. - Optimize query routing and context engineering across model tiers to balance latency, accuracy, and token spend. - Design automated evaluation harnesses integrated into CI/CD pipelines to continuously benchmark grounding, schema validity, and hallucination resistance against reference datasets. - Implement full-stack observability and defense-in-depth security, including field-level controls and automated PII scrubbing. - Lead technical delivery standards by establishing API interface contracts, specification-driven development patterns, and architectural blueprints for cross-functional engineering teams and executive stakeholders.

Requirements - 7+ years of hands-on enterprise software engineering experience using Python, TypeScript or Node.js, Java, or Apex. - 3+ years of direct production experience building, evaluating, and scaling LLM-powered applications and autonomous multi-agent workflows. - Expert proficiency with LangGraph and LangChain, frontier LLM APIs (including tool calling, prompt caching, and code-generation variants), MCP, and observability tools such as LangSmith, Langfuse, or OpenTelemetry. - Hands-on experience with automated LLM evaluation suites, including prompt-testing frameworks, RAG-quality scoring, or LLM-as-a-judge patterns used as automated test gates. - An ownership mindset with deep diagnostic debugging skills for isolating non-deterministic LLM behavior, context degradation, and latency bottlenecks. - Strong consultative communication ability to translate complex AI mechanics into actionable architecture roadmaps for technical and non-technical stakeholders. - Fluent written and spoken professional English for direct client consultation.

Nice to have - Practical integration experience with major CRM APIs, query languages, platform events, and connected apps. - Familiarity with data cloud offerings, vector search capabilities, or agent-style architectural patterns. - Experience deploying containerized MCP servers within enterprise CRM security boundaries. - Hands-on exposure to specification-driven development methodologies for AI-assisted software delivery workflows.

Benefits and work setup Candidates must be legally authorized to work in the United States, with no visa sponsorship available. The compensation package includes medical, dental, and vision insurance, a retirement plan, paid time off, and a posted salary range of $190,000 to $250,000 per year.