AI Engineer

AI Engineer – GenAI / RAG / Agentic AI

Location: Washington, DC (Hybrid – 4 Days Onsite)
Job Type: Contract

About Us

is a leading technology staffing and consulting firm connecting top talent with innovative organizations across the U.S. We specialize in delivering high-quality IT professionals for enterprise digital transformation, cloud, AI, and software engineering initiatives.

Job Summary

STAFFXPERT LLC is seeking an AI Engineer on behalf of our client in Washington, DC. This role is ideal for a hands-on engineer with strong software development experience and deep expertise in Generative AI, Retrieval-Augmented Generation (RAG), Agentic AI systems, and cloud-native AI platforms across Azure and AWS.

The ideal candidate will have experience designing and deploying scalable AI applications, secure multi-agent systems, and enterprise-grade AI infrastructure in production environments.

Key Responsibilities

• Design and implement enterprise-scale RAG pipelines using Azure AI Search, vector databases, embeddings, semantic/hybrid search, and re-ranking strategies.

• Develop secure conversational AI and multi-agent solutions using frameworks such as:

  • Semantic Kernel

  • AutoGen

  • LangChain

  • CrewAI

  • Microsoft Agent Framework

• Build and integrate Model Context Protocol (MCP) services with governance, RBAC, audit logging, and secure tool-calling capabilities.

• Develop scalable ingestion, ETL/ELT, and vectorization pipelines using Azure and AWS data platforms.

• Work with Azure AI Agent Service and cloud-native AI infrastructure across Azure and AWS ecosystems.

• Optimize LLM performance, latency, safety, and operational cost through evaluation frameworks and monitoring.

• Implement CI/CD pipelines, automated testing, observability, and security best practices for AI workloads.

• Collaborate with cross-functional teams including engineering, product, security, and platform teams.

Required Qualifications

• 6+ years of software engineering experience with strong development fundamentals.

• 2+ years of hands-on experience with GenAI/LLM technologies in production environments.

• Strong programming experience in:

  • Python

  • C#

  • .NET

• Experience building enterprise AI applications using:

  • RAG architectures

  • Vector databases

  • Embeddings and semantic search

  • Multi-agent orchestration

• Hands-on experience with Azure technologies including:

  • Azure OpenAI

  • Azure AI Search

  • Azure ML

  • AKS

  • Azure Functions

  • Azure Data Factory

  • Azure Databricks

• Experience with AWS services such as:

  • Bedrock

  • SageMaker

  • Lambda

  • API Gateway

  • EKS

  • EMR

• Strong understanding of:

  • Distributed systems

  • Secure coding practices

  • CI/CD

  • Performance optimization

  • AI governance and observability

Preferred Qualifications

• Experience with Hugging Face, MLflow, Ollama, vLLM, or Triton.

• Knowledge of vector search optimization (HNSW/IVF) and GPU scheduling.

• Experience with Responsible AI governance and AI safety frameworks.

• Familiarity with multi-cloud AI deployments and Kubernetes-based AI infrastructure.

• Relevant cloud and AI certifications are a plus.