Position: AI/Machine Learning Engineer
Location: Dearborn, MI (Hybrid)
Employment Type: Full-Time Contract
Pay: $64-66 per hour
Description: We are seeking an AI / Machine Learning Engineer to design, develop, and deploy production-grade multi-agent AI systems on Google Cloud Platform. This role focuses on building scalable agent orchestration frameworks, Retrieval-Augmented Generation (RAG) pipelines, intelligent automation solutions, and LLM-powered applications that transform complex data into actionable insights.
Responsibilities:
- Design and deploy production-ready multi-agent architectures using frameworks such as LangGraph, CrewAI, or LlamaIndex.
- Develop AI solutions leveraging LLMs, deep learning, NLP, generative AI, intelligent automation, and cognitive computing technologies.
- Build and optimize RAG pipelines, including embeddings, vector databases, hybrid retrieval, reranking, and retrieval evaluation.
- Integrate and govern BigQuery-based data access, ensuring secure, validated, and least-privilege execution of AI-generated SQL.
- Deploy AI services on GCP using Cloud Run, GKE, Vertex AI, Pub/Sub, Docker, Kubernetes, and CI/CD pipelines.
- Implement observability, evaluation, and monitoring frameworks using tools such as LangSmith, Langfuse, and OpenTelemetry.
- Develop guardrails, prompt-injection defenses, output validation, and human-in-the-loop approval workflows for safe AI operations.
- Optimize model cost, latency, and performance through model routing, caching, and scalable deployment strategies.
- Collaborate with data scientists and engineering teams to productionize AI prototypes and maintain reliable, monitored services.
Requirements:
- Bachelor’s degree in Computer Science, Software Engineering, or a related field.
- 3+ years of software development experience, including 1-2+ years building AI/ML or LLM-powered applications.
- Strong Python skills, including backend development with FastAPI or Flask.
- Experience building production multi-agent systems and distributed architectures.
- Hands-on experience with RAG architectures, vector databases (Pinecone, Weaviate, Qdrant, pgvector), embeddings, and retrieval evaluation.
- Experience with Google Cloud Platform (BigQuery, Cloud Run/GKE, Vertex AI, Pub/Sub).
- Strong SQL and cloud data warehouse experience.
- Proficiency with Docker, Kubernetes, GitHub Actions, and CI/CD methodologies.
- Knowledge of API design, testing, version control, security best practices, and LLM safety techniques.
Preferred:
- Master’s degree
- Experience with cost optimization and model-routing strategies.
- Human-in-the-loop workflows for high-reliability AI systems.
- Background in automotive, EV charging, IoT, or connected vehicle data.
- Familiarity with Model Context Protocol (MCP) or similar agent integration standards.
- Startup or 0-to-1 product development experience.
#LI-GL1