AI Software Engineer at Ford Motor Company

Wayne State University; United States; Sur place; USD 140 000 - 200 000; Plein temps

Résumé du poste

Ford Motor Company seeks an AI Software Engineer to design, build, deploy, and operate agentic applications powered by large language models. You will own the AI DevOps lifecycle, including prompts, configurations, model versions, and automated evaluation, within enterprise AI services like Vertex AI.

You will collaborate with Product Managers, Data Scientists, Designers, and other Engineers to release early and often, ensuring scalable, secure, and cost-efficient solutions for business

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, or a related technical discipline.
• 2+ years of software engineering experience building and operating production services with Python (or Java).
• 1+ year developing for and deploying to public cloud platforms — GCP preferred (Vertex AI / GenAI services, BigQuery, Cloud Run/Functions).
• Hands-on experience applying GenAI frameworks and services (e.g., Vertex AI Agent Builder, ADK, LangChain/LangGraph, LlamaIndex, function calling, RAG patterns) to build LLM-powered applications.
• 1+ year of DevOps experience with CI/CD tools and pipelines (e.g., Tekton, Cloud Build, Jenkins) and version control (Git).
• Working knowledge of containerization and orchestration (Docker, Kubernetes, GKE), including IaC concepts (e.g., Terraform).
• Understanding of LLMOps practices: prompt/model versioning, automated evaluation suites, and monitoring of LLM applications in production.

Responsabilités

• Design, develop, test, and deploy agentic applications that orchestrate foundation models to reason, plan, call tools/APIs, and execute multi-step business workflows
• Industrialize the AI delivery lifecycle (AI DevOps / LLMOps): standardize pipelines and CI/CD/CT for prompts, agent configurations, and model versions, with automated regression and evaluation gates before every release
• Build and integrate retrieval-grounded generation (embeddings, vector search, grounding against governed enterprise data sources such as BigQuery)
• Build robust REST APIs and containerized services that serve agent workloads with production-grade latency, cost, and throughput
• Implement observability: trace agent steps and tool calls, monitor quality and safety metrics, detect drift, and drive incident response with root cause analysis
• Apply guardrails, access controls, and responsible-AI practices in line with Ford data governance
• Practice software craftsmanship daily: paired programming, test-first development, code review, and living documentation
• Partner with PMs, Product Owners, Data Scientists, and Security to translate business problems into shippable agentic solutions, and share platform best practices, templates, and standards across teams

Connaissances

Python

GCP Vertex AI

LangChain

Docker

Kubernetes

CI/CD

DevOps

RAG patterns

Vector databases

Formation

Bachelor's degree in Computer Science

Bachelor's degree in Computer Engineering

Outils

Terraform

Git

BigQuery

Cloud Run

GKE

Description du poste

You are viewing a preview of this job. Log in or register to view more details about this job.

At Ford Motor Company, we believe freedom of movement drives human progress. We also believe in providing you with the freedom to define and realize your dreams. Creating the future of smart mobility requires the highly intelligent use of data, metrics, and analytics. That's where you can make an impact as part of our Global Data Insight & Analytics team. We are the trusted advisers that enable Ford to clearly see business conditions, customer needs, and the competitive landscape, driving evidence-based, timely decision-making.

The AI Software Engineer is a versatile developer responsible for designing, building, deploying, and operating software applications powered by large language models — agentic solutions that plan, reason, call enterprise tools and data, and complete business tasks end-to-end. You will work on a Balanced Product Team, collaborating directly with Product Managers, Data Scientists, Designers, and other Software Engineers, releasing early and often. You will own the AI DevOps lifecycle of these solutions: version-managed prompts, configurations, and models; automated evaluation; continuous deployment and training; monitoring; guardrails; and continuous improvement of quality, latency, and cost. The role leverages managed foundation models and enterprise AI services (e.g., GCP Vertex AI).

Responsibilities

• Design, develop, test, and deploy agentic applications that orchestrate foundation models to reason, plan, call tools/APIs, and execute multi-step business workflows
• Industrialize the AI delivery lifecycle (AI DevOps / LLMOps): standardize pipelines and CI/CD/CT for prompts, agent configurations, and model versions, with automated regression and evaluation gates before every release
• Build and integrate retrieval-grounded generation (embeddings, vector search, grounding against governed enterprise data sources such as BigQuery)
• Build robust REST APIs and containerized services (Docker, Cloud Run, Kubernetes/GKE) that serve agent workloads with production-grade latency, cost, and throughput
• Implement observability: trace agent steps and tool calls, monitor quality and safety metrics, detect drift, and drive incident response with root cause analysis
• Apply guardrails, access controls, and responsible-AI practices (groundedness checks, content safety, least-privilege tool access, PII handling) in line with Ford data governance
• Practice software craftsmanship daily: paired programming, test-first development, code review, and living documentation
• Partner with PMs, Product Owners, Data Scientists, and Security to translate business problems into shippable agentic solutions, and share platform best practices, templates, and standards across teams

Qualifications

Minimum Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, or a related technical discipline
• 2+ years of software engineering experience building and operating production services with Python (or Java)
• 1+ year developing for and deploying to public cloud platforms — GCP preferred (Vertex AI / GenAI services, BigQuery, Cloud Run/Functions)
• Hands-on experience applying GenAI frameworks and services (e.g., Vertex AI Agent Builder, ADK, LangChain/LangGraph, LlamaIndex, function calling, RAG patterns) to build LLM-powered applications
• 1+ year of DevOps experience with CI/CD tools and pipelines (e.g., Tekton, Cloud Build, Jenkins) and version control (Git)
• Working knowledge of containerization and orchestration (Docker, Kubernetes, GKE), including IaC concepts (e.g., Terraform)
• Understanding of LLMOps practices: prompt/model versioning, automated evaluation suites (groundedness, safety, latency), and monitoring of LLM applications in production

Preferred Skills

• Experience with orchestration tooling (Airflow, Kubeflow, Vertex Pipelines) and ML/LLM tracking and evaluation tools (MLflow, Weights & Biases, promptfoo or similar)
• Familiarity with vector databases and embedding pipelines, multi-agent orchestration, and enterprise tool integration (MCP or similar tool-calling patterns)
• DevSecOps exposure (e.g., Checkmarx, SAST/SCA pipelines) and experience with IAM, RBAC, and data protection standards (GDPR, CCPA)
• Experience working in Balanced Product Teams / Agile delivery (Rally or similar), paired programming, and TDD
• Familiarity with generative-AI evaluation and responsible-AI frameworks; knowledge of common ML concepts (Sklearn, TensorFlow, PyTorch) sufficient to collaborate with Data Scientists
• GCP certification (Professional Cloud Developer / Cloud Engineer) a plus