FH - Staff Agentic AI Engineer
About the Company
We are partnering with a fast-growing AI-native logistics technology company transforming how freight operations, carrier coordination, and transportation workflows are managed at scale. The company operates at the intersection of AI agents, human operations, and logistics execution — building systems that automate highly operational and communication-heavy workflows traditionally handled manually by freight brokers and operations teams. Rather than selling traditional SaaS software alone, the organization delivers AI-powered operational infrastructure deeply embedded into customer workflows and Transportation Management Systems (TMS). Their platform combines autonomous agents, workflow orchestration, voice AI, retrieval systems, and human-in-the-loop operations to help logistics organizations scale operational capacity without scaling headcount proportionally. With several large enterprise customers already onboarded and additional major deployments underway, the company is investing heavily in agentic infrastructure, distributed systems, workflow automation, voice interfaces, AI reliability, and operational orchestration.
About the Role – Staff Agentic AI Engineer
Reporting directly into technical leadership and working closely with founders, the Staff Agentic AI Engineer will play a foundational role in architecting and scaling the company’s next-generation AI operations platform. This is a highly senior, hands-on engineering role focused on building autonomous and semi-autonomous AI systems that operate within real-world logistics and operational workflows. You will help design and evolve distributed agentic systems capable of handling communication workflows, operational tracking, document extraction, escalation management, workflow orchestration, and AI-driven operational execution. We are specifically looking for someone deeply immersed in modern AI-native engineering workflows and agentic coding systems. The ideal candidate already operates daily using tools and environments such as Claude, Codex, Hermes Agent, OpenClaw, MCP servers, and autonomous software engineering agents as part of their development lifecycle. This role requires someone highly autonomous, product-minded, and comfortable operating in ambiguity while helping define the technical foundations of a rapidly scaling AI-native organization. The ideal candidate combines deep backend and distributed systems expertise with strong AI systems thinking, operational pragmatism, and a passion for building reliable production-grade autonomous systems.
Role & Responsibilities
Agentic AI Systems & Autonomous Workflows
- Design, build, and evolve autonomous AI agents operating across complex operational workflows.
- Architect backend agentic systems capable of orchestrating multi-step operational tasks with minimal human intervention.
- Build scalable AI workflows capable of handling escalation routing, exception management, and operational decision-making.
- Design systems enabling non-technical operational teams to safely modify and manage workflow logic without requiring engineering support.
- Help define the company’s long-term architecture for AI-native operational execution and orchestration.
Voice AI & Ambient Agents
- Build and scale voice-based AI agents supporting real-time operational communication workflows.
- Develop ambient AI systems capable of monitoring, interpreting, and reacting to operational events in real time.
- Improve conversational reliability, escalation handling, orchestration logic, and voice interaction quality across production systems.
- Work on systems involving conversational memory, workflow continuity, and real-time operational decision orchestration.
- Contribute to next-generation AI interaction layers combining voice, workflows, retrieval systems, and autonomous execution.
Distributed Systems & Backend Infrastructure
- Architect distributed systems supporting high-throughput asynchronous AI workflows.
- Design and operate queue-based architectures, message brokers, event-driven pipelines, and workflow orchestration systems.
- Build resilient backend services capable of supporting large-scale AI execution and monitoring.
- Improve observability, fault tolerance, and operational reliability across AI infrastructure.
- Design scalable infrastructure for autonomous workflow execution and multi-agent coordination.
AI Engineering, Evals & Reliability
- Build evaluation systems, benchmarking pipelines, and monitoring frameworks around AI agent performance and reliability.
- Develop tooling and infrastructure for continuous agent testing, prompt evaluation, workflow validation, and operational QA.
- Create scalable mechanisms for monitoring hallucinations, workflow failures, escalation quality, and operational risk.
- Help establish engineering standards around AI reliability, safety, observability, and production readiness.
- Partner closely with operational teams to improve real-world AI system performance.
AI-Native Engineering & Agentic Coding
- Operate daily using AI-native engineering workflows powered by Claude, Codex, Hermes Agent, OpenClaw, MCP servers, and related agentic systems.
- Help define internal best practices for AI-assisted software engineering and autonomous development workflows.
- Build internal AI tooling that accelerates engineering velocity, testing, deployment, and operational visibility.
- Push the boundaries of what high-performance software engineering looks like in an AI-native organization.
- Contribute across the stack when necessary, including lightweight frontend interfaces for workflow visualization, operational tooling, and internal AI management systems.
Workflow Automation & Operational Scaling
- Design systems capable of scaling highly customized operational SOPs across multiple enterprise customers.
- Build flexible workflow orchestration layers supporting customer-specific operational logic and AI behavior customization.
- Develop document extraction and operational intelligence systems leveraging structured and unstructured data.
- Help operationalize AI systems that integrate deeply into customer TMS, communication platforms, and operational ecosystems.
- Support rapid iteration cycles from MVP experimentation through production-scale deployment.
What We’re Looking For
Must-Haves
- 10+ years of software engineering experience with deep backend and distributed systems expertise.
- Extensive experience as a Staff, Principal, or Senior-level Engineer within AI infrastructure, distributed systems, platform engineering, or backend-heavy environments.
- Strong experience building AI-native systems, autonomous workflows, or agentic architectures in production environments.
- Deep understanding of asynchronous systems, queues, message brokers, event-driven architectures, and distributed execution models.
- Strong proficiency in Python, TypeScript, and modern backend engineering practices.
- Hands-on experience building or operating LLM-powered systems, RAG pipelines, AI orchestration layers, or conversational AI platforms.
- Deep passion for agentic coding and AI-native software engineering workflows.
- Strong hands-on usage of tools such as Claude, Codex, Hermes Agent, OpenClaw, MCP servers, or similar autonomous coding systems.
- Experience building evaluation frameworks, testing infrastructure, or monitoring systems around AI applications.
- Strong product mindset with ability to operate independently in highly ambiguous environments.
- Strong culture of testing, observability, operational reliability, and engineering craftsmanship.
- Ability to move quickly while maintaining strong architectural judgment and operational quality.
Nice-to-Haves
- Experience with voice AI, conversational systems, or real-time communication infrastructure.
- Experience building systems for logistics, freight, marketplaces, or operationally complex industries.
- Exposure to Transportation Management Systems (TMS) or logistics operations.
- Experience designing workflow builders or no-code/low-code operational systems.
- Experience with multi-agent orchestration systems and autonomous workflow execution.
- Familiarity with MCP server architectures and AI tool ecosystems.
- Experience supporting AI systems requiring high operational accountability and human-in-the-loop escalation models.
- Experience scaling AI infrastructure in early-stage or hypergrowth startup environments.
Location
- Remote-first environment
- Latin America strongly preferred
Why Join?
- Help build one of the next-generation AI-native operational platforms in a massive global industry.
- Operate at the frontier of agentic systems, autonomous workflows, voice AI, and AI-native engineering.
- Work directly on real-world AI execution problems with immediate operational and customer impact.
- Join a highly technical and product-driven environment with significant ownership and autonomy.
- Influence foundational architectural decisions during a critical scaling phase.
- Build systems that combine AI agents and human operations to transform operational workflows at scale.
Application Instructions
Please submit:
- Your résumé/CV
- GitHub, portfolio, research, or technical project examples
- Examples of AI systems, agentic architectures, workflow orchestration platforms, or distributed systems you have built
- Details about your experience using AI-assisted or autonomous coding systems in production environments
- Examples of evals, monitoring systems, or operational AI reliability initiatives you have led
- Your availability and compensation expectations
- Brief summary of your experience building scalable AI-native systems in production environments