> Markdown version of [/jobs/ext/4800441-full-stack-ai-software-engineer](https://www.wearedevelopers.com/jobs/ext/4800441-full-stack-ai-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Full Stack AI Software Engineer - **Company:** Ford Motor Company - **Location:** Louisville, KY, United States - **Experience:** Experienced - **Salary:** $74,300 - $124,500 - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Java (Programming Language), Admin Tools, Application Programming Interfaces (APIs), Artificial Intelligence, User Authentication, Microsoft Azure, C Sharp (Programming Language), Cloud Computing, Code Generation, Code Review, Collaborative Software, Continuous Integration, Data Stores, Relational Databases, Cursor, Graph Database, Push Technology, Python (Programming Language), PostgreSQL, MySQL, Node.Js, OAuth, Redis, OpenAI, Next.js, Search Technologies, Single Sign-On, Software Engineering, SQL Databases, TypeScript, Management of Software Versions, Web Application Frameworks, WebSocket, Openapi, Data Logging, Pinecone, Google Cloud, GitHub Copilot, ReactJS, Retrieval-Augmented Generation, Large Language Models, Claude Code, Multi-Agent Systems, AI Coding Agents, Backend, Agentic-AI, Rate Limiting, Event Driven Architecture, Pgvector, Information Technology, Performance Monitor, Weaviate, Graphql, Front End Software Development, Virtual Agents, Api Gateway, Restful APIs, Grpc, Industrial Software, Automation Anywhere, Golang, Programming Languages, Microservices, Agent2Agent Protocol - **Published:** November 20, 2026 - **Apply:** https://www.careerbuilder.com/job-details/full-stack-ai-software-engineer-louisville-ky--43b4fb60-3ec9-4d4f-afe5-e5f9cdba36a0 ## About the Role Software Engineering, Artificial Intelligence (AI), Manufacturing, Leading Edge Technology, Software Engineering, Artificial Intelligence (AI), Artificial Intelligence (AI) Agents, Application Programming Interface (API), Manufacturing Software, Artificial Intelligence (AI) Programming Languages, * Bachelor''s degree in Computer Science, Software Engineering, Data Science, or a related field, or equivalent experience. * 3+ years shipping full-stack applications in production. * Strong front-end skills with a modern web or mobile framework, plus proficiency in at least one back-end language (e.g., Go, Python, Java, TypeScript, C#), and strong SQL. * Designing REST or GraphQL APIs and services, relational databases, and authentication (OAuth, single sign-on), using OpenAPI specs, versioning, error handling, and rate limiting. * Hands-on experience building with LLMs: prompting, retrieval-augmented generation, tool use, and agent frameworks. * Evaluating model or system output; testing, CI/CD, and code review. Even better, you may have... * Agent frameworks (e.g., LangGraph, Google ADK) and protocols (MCP, A2A); multi-agent systems. * Vector databases, embeddings, and semantic search; knowledge graphs or ontologies. * LLM observability and cost management (e.g., OpenTelemetry, Logfire, token budgets). * Real-time features (websockets, push notifications, event streams), gRPC, API gateways, and publishing SDKs; collaboration platform integration (e.g., Microsoft Teams). * Cloud platforms (e.g., Google Cloud: Cloud Run, GKE, Pub/Sub, Vertex AI), containers, and infrastructure as code. * Daily use and customization of AI coding agents, with current knowledge of LLM models and their trade-offs. * Apps for front-line workers; manufacturing, quality, or structured problem-solving experience (8D, 5-Why). ## Description * Supervisors and engineers run their work in our applications, act on agent recommendations, and confirm fixes. * Agents complete investigation steps reliably, with sources shown and confidence stated; evaluation, cost, and latency improve release over release. * Releases ship regularly with low error and crash rates; new plant data sources plug in without client rework. * Other teams, AI agents, and coding agents build on the platform''s APIs, SDKs, and agent interfaces without duplicate apps, APIs, or data stores., * Build features end to end: web and mobile clients, back-end APIs, SDKs, and services. * Build and orchestrate AI agents grounded in plant data a person can check. * Measure agent quality, cost, and latency, and improve them release over release. * Set up coding agents to build new features on the platform''s approved SDKs and APIs. * Spend time with supervisors and engineers on the plant floor and turn what you see into the next release. Frontend Development (Web & Mobile) * Build responsive, high-performance interfaces with modern web frameworks (e.g., React, Next.js), plus mobile clients (native or cross-platform) and admin tools. * Design for the plant floor: noise, gloves, poor connectivity, and shift handoffs. Build issue, escalation, alert, and team communication flows. * Show AI agent recommendations with their sources and confidence. Backend & API Engineering * Design scalable microservices, RESTful/GraphQL/gRPC APIs, and event-driven architectures in any modern back-end language (e.g., Go, Python, Java, TypeScript/Node.js, C#), choosing the right tool for the job. * Own versioned, documented (OpenAPI), secure, backward-compatible APIs and SDKs that other teams and coding agents build on. * Connect applications to production, maintenance, and quality systems and collaboration tools; handle identity, permissions, and privacy for plant users. AI & Agentic Integration * Connect production applications to LLM providers (e.g., OpenAI, Anthropic, Azure OpenAI, Vertex AI), routing models by task, cost, latency, and risk. * Build agents that classify issues, plan investigations, call tools, and draft recommendations, using ReAct, tool-calling, structured outputs, and multi-agent workflows with clear hand-offs and stopping rules. * Build agent-to-agent services (MCP, A2A) so agents can call applications and plant tools, share context, and hand off tasks securely. * Ground every answer in the application''s own data, choosing the right retrieval method (APIs, SQL, RAG, keyword, or vector search); have agents flag low confidence or missing data and hand off to a person. Data & Vector Infrastructure * Manage relational and caching stores (e.g., PostgreSQL, MySQL, Redis) alongside vector databases (e.g., pgvector, Pinecone, Weaviate) for semantic search and agent memory. * Build RAG pipelines (chunking, embeddings, ranking, filtering) over plant and platform knowledge, connected to manufacturing ontologies and knowledge graphs. Evaluation, Token Economics & Observability * Test agents against shared evaluation sets before each release, add cases from plant experts, and turn confirmed fixes into better agent behavior. * Track prompt performance, manage token budgets, and optimize accuracy, cost, and response time. * Instrument AI workflows with telemetry and tracing (e.g., OpenTelemetry, Logfire) alongside logging, error, and performance monitoring. Coding Agent Harness & Delivery * Configure coding agents (e.g., Claude Code, GitHub Copilot, OpenCode, Cursor, Codex) with instructions, skills, MCP tools, and guardrails so new features extend existing applications and reuse their APIs, SDKs, and data stores. * Enforce reuse with automated checks and benchmark tasks; hold AI-generated code to the same bar as any code: tests, review, security checks, and CI/CD gates. * Release through CI/CD, monitor production, and fix issues fast. What you''ll do... A hands-on role on a small team that ships often. You will: * Build features end to end: web and mobile clients, back-end APIs, SDKs, and services. * Build and orchestrate AI agents grounded in plant data a person can check. * Measure agent quality, cost, and latency, and improve them release over release. * Set up coding agents to build new features on the platform''s approved SDKs and APIs. * Spend time with supervisors and engineers on the plant floor and turn what you see into the next release. Frontend Development (Web & Mobile) * Build responsive, high-performance interfaces with modern web frameworks (e.g., React, Next.js), plus mobile clients (native or cross-platform) and admin tools. * Design for the plant floor: noise, gloves, poor connectivity, and shift handoffs. Build issue, escalation, alert, and team communication flows. * Show AI agent recommendations with their sources and confidence. Backend & API Engineering * Design scalable microservices, RESTful/GraphQL/gRPC APIs, and event-driven architectures in any modern back-end language (e.g., Go, Python, Java, TypeScript/Node.js, C#), choosing the right tool for the job. * Own versioned, documented (OpenAPI), secure, backward-compatible APIs and SDKs that other teams and coding agents build on. * Connect applications to production, maintenance, and quality systems and collaboration tools; handle identity, permissions, and privacy for plant users. AI & Agentic Integration * Connect production applications to LLM providers (e.g., OpenAI, Anthropic, Azure OpenAI, Vertex AI), routing models by task, cost, latency, and risk. * Build agents that classify issues, plan investigations, call tools, and draft recommendations, using ReAct, tool-calling, structured outputs, and multi-agent workflows with clear hand-offs and stopping rules. * Build agent-to-agent services (MCP, A2A) so agents can call applications and plant tools, share context, and hand off tasks securely. * Ground every answer in the application''s own data, choosing the right retrieval method (APIs, SQL, RAG, keyword, or vector search); have agents flag low confidence or missing data and hand off to a person. Data & Vector Infrastructure * Manage relational and caching stores (e.g., PostgreSQL, MySQL, Redis) alongside vector databases (e.g., pgvector, Pinecone, Weaviate) for semantic search and agent memory. * Build RAG pipelines (chunking, embeddings, ranking, filtering) over plant and platform knowledge, connected to manufacturing ontologies and knowledge graphs. Evaluation, Token Economics & Observability * Test agents against shared evaluation sets before each release, add cases from plant experts, and turn confirmed fixes into better agent behavior. * Track prompt performance, manage token budgets, and optimize accuracy, cost, and response time. * Instrument AI workflows with telemetry and tracing (e.g., OpenTelemetry, Logfire) alongside logging, error, and performance monitoring. Coding Agent Harness & Delivery * Configure coding agents (e.g., Claude Code, GitHub Copilot, OpenCode, Cursor, Codex) with instructions, skills, MCP tools, and guardrails so new features extend existing applications and reuse their APIs, SDKs, and data stores. * Enforce reuse with automated checks and benchmark tasks; hold AI-generated code to the same bar as any code: tests, review, security checks, and CI/CD gates. * Release through CI/CD, monitor production, and fix issues fast.