Senior AI Platform Engineer — Cloud-Native LLM & RAG Expert

Apex Systems; Dearborn (MI); Hybrid; USD 140,000 - 180,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

Everforth Apex Systems is seeking a Senior AI Platform Engineer to design, develop, and deploy AI-powered applications, multi-agent systems, and automation solutions using Generative AI, LLMs, RAG, NLP, and cloud-native tech. The role blends software engineering, cloud architecture, and AI development to deliver scalable, secure, observable, production-ready solutions.

The candidate will build cloud-native AI services on GCP (Cloud Run, GKE, Vertex AI, BigQuery, Pub/Sub), establish CI/CD

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Data Science, or a related field.
• 3+ years of experience developing and deploying production software systems.
• 1-2+ years of experience building and supporting AI, machine learning, generative AI, or LLM-powered applications.
• Experience designing and deploying multi-agent, distributed, or service-oriented architectures in production environments.
• Strong Python programming skills, including asynchronous and concurrent application development.
• Experience with backend frameworks such as FastAPI or Flask.
• Hands-on experience with agent orchestration frameworks such as LangGraph, CrewAI, LlamaIndex, or similar technologies.
• Experience building and optimizing RAG solutions, including vector databases, embeddings, chunking strategies, and retrieval evaluation.
• Experience with vector databases such as Pinecone, Weaviate, Qdrant, or pgvector.
• Experience deploying solutions to cloud platforms, preferably Google Cloud Platform.
• Strong SQL and cloud data warehouse experience.
• Experience with containerization and cloud-native deployment technologies, including Docker and Kubernetes.
• Experience building evaluation, monitoring, and observability frameworks for AI applications.
• Understanding of AI safety principles, prompt injection protection, output validation, and secure execution practices.
• Strong software engineering fundamentals, including testing, API design, version control, scalability, security, and coding best practices.

Responsibilities

• Design, architect, and deploy production-grade multi-agent AI systems using modern orchestration frameworks and state management capabilities.
• Develop intelligent applications, cognitive services, and AI-powered workflows that automate processes, generate recommendations, identify patterns, predict outcomes, and enable self-service capabilities.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embeddings, hybrid retrieval, reranking, and retrieval evaluation.
• Develop and maintain secure integrations between AI applications, enterprise data platforms, and operational systems.
• Design, implement, and optimize AI models and algorithms to solve complex business and operational challenges.
• Build and maintain cloud-native AI services on Google Cloud Platform, including Cloud Run, GKE, Vertex AI, BigQuery, and Pub/Sub.
• Establish CI/CD pipelines, containerized deployments, infrastructure automation, and software delivery best practices.
• Implement observability, monitoring, evaluation frameworks, and tracing capabilities for AI and agent-based systems.
• Develop guardrails, validation mechanisms, prompt security controls, and human-in-the-loop workflows to ensure safe and reliable AI operations.
• Collaborate with data scientists, software engineers, product teams, and business stakeholders to operationalize AI solutions.
• Drive performance, scalability, reliability, and cost optimization strategies across AI platforms and services.
• Research emerging AI technologies and evaluate opportunities to enhance organizational capabilities and business outcomes.

Job description

Everforth Apex Systems is seeking a Senior AI Platform Engineer to design, develop, and deploy AI-powered applications, multi-agent systems, and automation solutions using Generative AI, LLMs, RAG, NLP, and cloud-native tech. The role blends software engineering, cloud architecture, and AI development to deliver scalable, secure, observable, production-ready solutions.

The candidate will build cloud-native AI services on GCP (Cloud Run, GKE, Vertex AI, BigQuery, Pub/Sub), establish CI/CD