Senior AI Engineer (Generative AI / RAG / Agentic AI)
Globenet Consulting Corp·Washington, US
Posted 6 days ago
Full-Time
Apply Now About the Role
About the position
We are seeking a Senior AI Engineer to architect and deliver secure, scalable, production-grade Generative AI solutions. You will design and implement RAG systems, agentic AI orchestration, and cloud-native ML infrastructure across Azure and AWS. This role blends hands-on engineering with technical leadership, including mentoring and setting reusable engineering standards.
Responsibilities
• Architect and deliver enterprise GenAI, RAG, and conversational AI solutions end-to-end
• Design scalable retrieval, prompting, and inference patterns across Azure and AWS
• Build ingestion, enrichment, vectorization, and feature pipelines using Databricks, ADF, and EMR
• Implement embedding quality checks, drift monitoring, and metadata governance
• Engineer secure multi-agent/tool-calling systems using modern agent frameworks and MCP controls
• Establish evaluation, safety guardrails, CI/CD, automated testing, and observability for AI workloads
• Apply secure AI engineering practices, including threat modeling and compliance-aligned controls
• Lead design reviews, code reviews, and mentor engineers; create reference architectures and playbooks
Requirements
• Bachelor’s in CS/Engineering (Master’s preferred)
• 8+ years of software engineering experience
• 2+ years building applied Generative AI solutions (RAG, agents, evaluation/safety) in production
• Azure: Azure OpenAI, Azure AI Search, Azure AI Agent Service, Azure ML, AKS, ADF, Databricks, Functions, API Mgmt, Key Vault, App Insights
• AWS: SageMaker, Bedrock, Lambda, API Gateway, S3, CloudWatch, EMR, EKS, CodePipeline, Outposts
• Vector/Indexing: Azure AI Search, Redis, FAISS, HNSW, IVF
• Frameworks: Semantic Kernel, AutoGen, Microsoft Agent Framework, CrewAI, Agno, LangChain, MCP, Hugging Face
• Languages: Python, C#, .NET, TypeScript
• Inference/Deploy: Docker, vLLM, Triton, Ollama, quantized Llama (GGUF), GPU scheduling, multimodal pipelines
• MLOps/Platform: MLflow, evaluation tooling, guardrails, Azure DevOps pipelines, Kubernetes, hybrid/multi-cloud
• AI-900, DP-900, Responsible AI Certification, AWS ML Specialty, TensorFlow Developer, CKA/CKAD, SAFe Agile Software Engineering
Nice-to-haves
• AI-102, DP-100, AZ-305, AZ-204
Benefits
• Competitive salary
• Opportunity for advancement
• Training & development
What you'll do
- You will design and implement RAG systems, agentic AI orchestration, and cloud-native ML infrastructure across Azure and AWS
- This role blends hands-on engineering with technical leadership, including mentoring and setting reusable engineering standards
- Architect and deliver enterprise GenAI, RAG, and conversational AI solutions end-to-end
- Design scalable retrieval, prompting, and inference patterns across Azure and AWS
- Build ingestion, enrichment, vectorization, and feature pipelines using Databricks, ADF, and EMR
- Implement embedding quality checks, drift monitoring, and metadata governance
- Engineer secure multi-agent/tool-calling systems using modern agent frameworks and MCP controls
- Establish evaluation, safety guardrails, CI/CD, automated testing, and observability for AI workloads
- Apply secure AI engineering practices, including threat modeling and compliance-aligned controls
- Lead design reviews, code reviews, and mentor engineers; create reference architectures and playbooks
Requirements
- 8+ years of software engineering experience
- 2+ years building applied Generative AI solutions (RAG, agents, evaluation/safety) in production
- Azure: Azure OpenAI, Azure AI Search, Azure AI Agent Service, Azure ML, AKS, ADF, Databricks, Functions, API Mgmt, Key Vault, App Insights
- AWS: SageMaker, Bedrock, Lambda, API Gateway, S3, CloudWatch, EMR, EKS, CodePipeline, Outposts
- Vector/Indexing: Azure AI Search, Redis, FAISS, HNSW, IVF
- Frameworks: Semantic Kernel, AutoGen, Microsoft Agent Framework, CrewAI, Agno, LangChain, MCP, Hugging Face
- Languages: Python, C#, .NET, TypeScript
- Inference/Deploy: Docker, vLLM, Triton, Ollama, quantized Llama (GGUF), GPU scheduling, multimodal pipelines
- MLOps/Platform: MLflow, evaluation tooling, guardrails, Azure DevOps pipelines, Kubernetes, hybrid/multi-cloud
- AI-900, DP-900, Responsible AI Certification, AWS ML Specialty, TensorFlow Developer, CKA/CKAD, SAFe Agile Software Engineering
Benefits
- Competitive salary
- Opportunity for advancement
- Training & development