Ml Platform Engineer Jobs in Tennessee (NOW HIRING)

Build and operate the execution systems that power real-world logistics workflows — workflow orchestration, durable event-driven pipelines, and safe agentic behaviors across the Navion platform.

Navion helps logistics operators move from reactive, labor-heavy workflows toward more efficient, increasingly agentic operations. The Navion Logistics Platform removes friction across the order-to-cash workflow by connecting planning, ordering, execution, visibility, and billing into a more continuous operational flow.

Our platform includes four connected components: KeepFill (Inventory Intelligence & Automated Replenishment), SPOT (Unstructured Order Intake Turned into Actionable Work), Portal (Real-Time Visibility Across Orders and Documents), and BackOffice (Order-to-Invoice Reconciliation and Billing Readiness).

Navion works alongside existing TMS and document systems, helping carriers reduce manual work, improve workflow continuity, and scale without adding unnecessary complexity.

As we continue building the operational infrastructure for increasingly agentic logistics workflows, we are creating the execution layer that allows AI-driven systems to operate in controlled, reliable, production-grade environments.

Navion is seeking an Agentic Platform Engineer to build and operate the execution systems that power real-world logistics workflows across the Navion platform.

This role sits at the intersection of systems engineering, workflow orchestration, and applied AI. The Agentic Platform Engineer will help design the durable operational layer that turns unstructured inputs into structured state, coordinates work across systems and people, and enables safe agentic execution inside dispatch, visibility, and back‑office workflows.

This is a foundational engineering role for Navion's next phase of platform development. It is ideal for someone who thinks in systems, designs for reliability, and wants to help define how AI can move real operational work forward under practical constraints.

This is the most AI‑native role on the team. The Agentic Platform Engineer we hire already builds with agents daily — uses Claude Code (or equivalent) as their primary development environment, has shipped production systems with tool use, structured outputs, and multi‑step agent loops, and holds real opinions on models, context engineering, evals, and where agents belong versus where deterministic code is still the right answer. We are not hiring someone who thinks LLMs are interesting. We are hiring someone operating at the frontier of what agents can reliably do — and who wants to push that frontier further inside real business operations.

• Build workflow orchestration systems that coordinate work across Navion's platform modules and external systems.
• Design durable, event‑driven pipelines that support complex operational workflows at production scale.
• Transform unstructured inputs such as emails, PDFs, texts, and documents into structured, actionable system events.
• Implement agentic workflow behaviors including planning, validation, retries, escalation paths, and human‑in‑the‑loop controls.
• Define system contracts, operational invariants, and failure‑handling patterns that support reliability and trust.
• Ensure strong observability across workflows through logging, tracing, replayability, and operational diagnostics.
• Help unify KeepFill, SPOT, Portal, and BackOffice into a cohesive execution layer across the Navion Logistics Platform.
• Collaborate closely with engineering, product, deployment, and customer‑facing teams to ensure systems are built for real operational conditions.
• Contribute to the technical architecture that enables Navion customers to move from manual coordination toward increasingly agentic operations.
• Design and maintain the eval infrastructure that keeps agentic behaviors trustworthy in production — golden datasets, regression tests, LLM‑as‑judge patterns, and drift monitoring as models change underneath us.
• Make opinionated calls about where LLMs belong versus where typed schemas, deterministic code, or traditional ML are the right tool — and write the code that enforces those boundaries.
• Use agents to build agents. Treat Claude Code, custom skills, MCP servers, and headless agent harnesses as first‑class parts of your development practice, and pull the rest of engineering up to the same bar.

You think in workflows, not just endpoints.

You design for operational reality, not ideal conditions.

You are comfortable building systems where reliability, auditability, and exception handling matter as much as speed.

You can bridge emerging AI capabilities with the practical constraints of real businesses and live operations.

You are motivated by building infrastructure that reduces friction, lowers manual effort, and helps teams operate with more control.

You have shipped production agentic systems at real user scale — with tool use, structured outputs, and enough failure modes to have sharp opinions about what actually works.

You write evals the way other engineers write tests. You do not trust agentic behavior you cannot measure, and you do not ship changes without a regression signal.

You are fluent at the current frontier — models, protocols, context engineering, harness design. You track this field because it moves weekly and you want to, not because your job demands it.

You use agents to build. Claude Code, custom skills, MCP servers, headless harnesses — these are how you ship, not novelties you have heard about.

• Strong backend or systems engineering experience in TypeScript, Python, or similar languages.
• Experience designing and operating distributed systems, event‑driven architectures, or workflow‑based platforms.
• Ability to build observable, debuggable, production‑grade systems with strong operational discipline.
• Experience working with APIs, integrations, and data flows across multiple systems.
• Deep, hands‑on experience building production systems with LLMs — tool use, structured outputs, multi‑step agent loops, retrieval, and evals. Not weekend experiments. Real systems with real users and real failure modes.
• Ability to reason clearly about system state, workflow continuity, resilience, and failure recovery.
• Strong communication skills and the ability to work across technical and non‑technical teams.
• Demonstrated practice building and maintaining eval harnesses for probabilistic systems. If "we spot‑check outputs" is your current answer to quality, this is not the right role.
• Active daily use of agentic coding tools (Claude Code, Cursor, or equivalent) — with concrete examples of custom skills, MCP servers, or harness extensions you have built and shared.
• Strong opinions on model selection, prompt and context engineering, and where agents reliably outperform deterministic code versus where they introduce more risk than they remove.

• Experience with Temporal or comparable workflow orchestration frameworks.
• Experience with document ingestion, OCR pipelines, or unstructured input processing.
• Experience in logistics, supply chain, transportation, or other operationally complex software environments.
• Familiarity with TMS integrations or workflow‑layer systems that sit across existing platforms.
• Experience building systems that operate under high variability, incomplete information, and frequent edge cases.
• Experience supporting human‑in‑the‑loop workflows where software and operations teams must work together.
• Built or contributed to MCP servers, custom agent harnesses, or open‑source agentic tooling.
• Experience with agent orchestration patterns beyond basic tool use — planner/executor splits, reflection loops, multi‑agent systems, or long‑horizon agentic workflows.
• Published work (blog posts, OSS, talks) on agentic systems, evals, or production LLM engineering.

Execution is becoming easier to generate. Reliable execution in real operational environments is not.

Navion is building the platform that helps logistics operators reduce friction across planning, ordering, visibility, and billing so work can move forward with less manual effort, fewer breakdowns, and greater consistency.

This is an opportunity to help define how agentic systems are introduced into live business operations in a way that is practical, trusted, and valuable. You will be building core infrastructure that shapes how AI actually functions inside real logistics workflows.