Agentic AI Engineer

Engagement Type: Full-Time / Contractor

CodeRoad is a technology execution partner trusted by companies across North America since 2002. We work alongside our clients to engineer, modernize, and scale the technology that powers their businesses, combining deep technical expertise, specialized teams, and shared accountability for outcomes. Our capabilities span product engineering, platform engineering, legacy modernization, and AI engineering.

Our engineers, designers, delivery leaders, and technology specialists collaborate through Velocity Studios: specialized teams developed within CodeRoad to deliver complex technology initiatives. Being assigned to a project means you become part of a collaborative environment where you can strengthen your expertise, take ownership of meaningful work, and grow alongside experienced professionals.

• High-Velocity Work & Client Exposure: We work close to the technology, teams and roadmaps that move real outcomes. Direct engagement with U.S. client teams and roadmaps.

• Career Continuity & Long-Term Opportunity: Your career here can outlast any single project. Continuous multi-project pipeline; long-tenure CodeRoaders.

• Engineering Autonomy & Technical Mastery: We invest in the skills that shape what's next. Agentic AI tools and training, Coursera Enterprise, Studio practice labs, L1-L7 Career Framework.

• High-Trust Employee Experience: You grow in an environment built on trust, transparency and recognition. High-touch onboarding, transparent leadership communication, community recognition, psychological safety.

• Architect Multi-Agent Systems: Design and deploy hierarchical multi-agent workflows using LangGraph, transitioning legacy single-prompt applications into modular, autonomous systems.

• Optimize Token Economics & Latency: Build domain-specific sub-agents featuring dynamic, on-demand context-loading mechanisms to streamline operational security, performance, and token costs.

• Standardize Agent Tooling: Integrate scalable tool-calling capabilities and standardized connectors using the Model Context Protocol (MCP).

• Implement Observability & Cost Tracking: Manage and configure LangFuse to maintain complete visibility over LLM reasoning traces, performance metrics, and cost allocation.

• Establish Automated Evaluation Harnesses: Lead the creation of regression testing suites and automated eval harnesses using tools like PromptFlow or PromptFoo against key benchmark datasets.

• Enforce OWASP AI Security Guardrails: Collaborate with security leads to integrate strict access controls and guardrail frameworks aligned with OWASP Top 10 standards for LLM applications.

• Software Engineering Depth: 5+ years of professional backend software development experience, primarily centered around Python and scalable architecture.

• Agentic AI & Orchestration Expertise: 2+ years of hands-on experience building production-grade AI agents or complex LLM workflows using LangGraph or LangChain.

• Modern AI & Foundation Model Stack: Deep experience working with foundation models (Anthropic Claude, OpenAI, Google Gemini), open-weights models, advanced prompt engineering, and the Microsoft 365 Agents SDK.

• Observability & Evaluation Proficiency: Direct experience setting up LLM observability platforms (LangFuse) and automated evaluation/testing frameworks.

• Cloud & Infrastructure Familiarity: Practical knowledge of containerized deployments using Docker across cloud platforms like Azure.

• Collaboration & Language: High ownership mindset, empathetic communication style, and advanced English proficiency (written and spoken) for direct engagement with U.S. engineering teams.

• USA Contractor / 100% Remote

• Competitive Pay (USD)

• Holidays Off & Paid Time Off

• Health insurance assistance program

• Opportunity to work with high-growth US-based companies and cutting-edge tech stacks.

Explore opportunities and submit your application today!