Note: The job is a remote job and is open to candidates in USA. CodeRoad is hiring a Lead Agentic AI Engineer to design and deploy enterprise autonomous agent systems and AI integrations. The role leads technical architecture, evaluation, security, observability, and engineering standards for client projects.
Responsibilities
- Architect Multi-Agent Orchestration Systems: Design and deploy stateful multi-agent coordination graphs using LangGraph or custom DAG loops, enabling dynamic task decomposition, supervisor orchestration, human-in-the-loop escalation, and self-healing error recovery
- Engineer MCP Interfaces & Connectors: Build standardized Model Context Protocol (MCP) servers and connectors to securely expose Salesforce tools, custom objects, actions, and enterprise context to autonomous agent runners
- Optimize Reasoning, Latency & Token Spend: Architect multi-tiered LLM routing strategies across model tiers (utilizing Claude 3.5 Sonnet/Opus for complex multi-turn reasoning and Haiku for high-throughput utility tasks) to balance latency, accuracy, and API costs
- Establish Automated Evaluation Pipelines: Implement automated eval harnesses (Promptfoo, Ragas, DeepEval) within CI/CD pipelines to continuously measure context grounding, schema validity, and hallucination resistance against golden benchmark datasets
- Enforce Defense-in-Depth Security & Observability: Implement end-to-end telemetry and security using LangSmith or Langfuse, combined with input sanitization, field-level security (FLS) compliance, and automated PII scrubbing
- Lead Technical Strategy & Architecture Standards: Establish specification-driven development patterns, clear API contracts, and architectural blueprints, communicating technical trade-offs directly to engineering teams and C-suite stakeholders
Skills
- 7+ Years of Enterprise Software Engineering: Proven experience building robust software systems in **Python**, **TypeScript / Node.js**, **Java**, or **Apex**
- 3+ Years of Production AI / LLM Experience: Demonstrated track record designing, evaluating, and scaling production autonomous agent systems and RAG architectures in enterprise environments
- Agentic AI & Tooling Mastery: Deep expertise with **LangGraph**, **LangChain**, **Anthropic / Claude APIs** (tool calling, prompt caching, Claude Code), **MCP**, and observability suites (**LangSmith**, **Langfuse**, **OpenTelemetry**)
- Rigorous Evaluation Mechanics: Direct experience setting up automated test gates using **Promptfoo**, **Ragas**, or **LLM-as-a-judge** frameworks to monitor non-deterministic behavior and context degradation
- Proactive Ownership & Diagnostic Skills: High autonomy to isolate complex latency bottlenecks, debug agent routing loops, and turn ambiguous enterprise needs into secure, deterministic technical realities
- Advanced English Fluency: Exceptional written and spoken English communication skills for direct technical leadership and consultation with U.S.-based client executives
- Legal Authorization: Legal authorization to work in the United States
- Hands-on experience with Salesforce APIs (REST, SOQL/SOSL, Platform Events), **Salesforce Data Cloud**, vector search, **Agentforce**, containerized MCP deployments, or Spec-Driven Development (SDD)
Benefits
- Comprehensive Benefits Package (Medical, Dental, Vision & Retirement Plan)
- Holidays Off & Paid Time Off (PTO)
- Opportunity to work with high-growth US-based companies and cutting-edge tech stacks.
Company Overview