About the Role
Note: The job is a remote job and is open to candidates in USA. CodeRoad provides end-to-end software development services, including infrastructure solutions, staff augmentation, dedicated IT teams, and software engineering services. The Lead Agentic AI Engineer will architect, build, and operationalize enterprise-grade autonomous agent systems integrated with Salesforce, leading multi-agent workflows, evaluation pipelines, observability, security, and technical delivery standards.
Responsibilities
Architect stateful multi-agent coordination graphs using LangGraph or custom DAG loops, supporting dynamic task decomposition, supervisor orchestration, human-in-the-loop escalation, and automated error recoveryBuild standardized MCP (Model Context Protocol) servers and connectors to securely expose Salesforce tools, objects, custom actions, and operational context to agent runnersOptimize query routes and context engineering across model tiers (such as Claude Sonnet/Opus for multi-turn reasoning vs. Haiku for high-throughput utility tasks) to optimize latency, accuracy, and token spendDesign automated evaluation harnesses (Promptfoo, Ragas, or DeepEval) integrated into CI/CD pipelines to continuously benchmark grounding, schema validity, and hallucination resistance against reference datasetsImplement full-stack observability and defense-in-depth security using tools like LangSmith or Langfuse alongside strict input sanitization, field-level security (FLS), and automated PII scrubbingLead technical delivery standards, establishing API interface contracts, specification-driven development patterns, and architectural blueprints for cross-functional engineering teams and executive stakeholders
Skills
7+ years of hands-on enterprise software engineering experience using Python, TypeScript/Node.js, Java, or Apex3+ years of direct production experience building, evaluating, and scaling LLM-powered applications and autonomous multi-agent workflowsExpert proficiency with LangGraph / LangChain, Anthropic/Claude APIs (tool calling, prompt caching, Claude Code), MCP, and observability tools (LangSmith, Langfuse, or OpenTelemetry)Hands-on experience with automated LLM eval suites (Promptfoo, Ragas, or LLM-as-a-judge patterns) as automated test gatesOwnership mindset with deep diagnostic debugging skills for isolating non-deterministic LLM behavior, context degradation, and latency bottlenecksStrong ability to translate complex AI mechanics into actionable architecture roadmaps for technical and non-technical stakeholdersFluent written and spoken professional English for direct client consultationCandidate must be legally authorized to work in the United States (no sponsorship available)Practical integration experience with Salesforce APIs (REST, Composite, Bulk), SOQL/SOSL, Platform Events, and Connected AppsFamiliarity with Salesforce Data Cloud, vector search capabilities, or Agentforce architectural patternsExperience deploying containerized MCP servers integrated with enterprise CRM security boundariesHands-on exposure to Spec-Driven Development (SDD) methodologies for AI-assisted software delivery workflows
Benefits
Medical insuranceDental insuranceVision insuranceRetirement planPaid time off (PTO)
Company Overview
At CodeRoad, we accelerate ROI through end-to-end software engineering and technology execution. It was founded in 2002, and is headquartered in Boca Raton, Florida, US, with a workforce of 201-500 employees. Its website is https://www.coderoad.com.