Senior AI Architect / Agentic AI Engineer (LLM & RAG Platforms)

Senior AI Architect / Agentic AI Engineer (LLM & RAG Platforms)

Location: Remote (USA)
Duration: W2 / C2C

Job Overview

We are seeking a Senior AI Architect / Agentic AI Engineer to design and build enterprise-scale LLM-powered platforms, agentic AI systems, and Retrieval-Augmented Generation (RAG) pipelines.

The ideal candidate will have deep experience developing production-grade AI systems, integrating LLMs with enterprise data systems, and designing scalable AI architectures using modern cloud and microservices technologies.

This role requires strong expertise in LLM orchestration, AI agents, backend engineering, and AI infrastructure design.

Key Responsibilities

• Design and develop LLM-powered enterprise applications, including RAG systems, AI assistants, and autonomous agent workflows.
• Architect agentic AI systems with planner-executor patterns, tool integrations, and reasoning workflows.
• Build scalable AI microservices using Python frameworks such as FastAPI or Flask.
• Develop and optimize vector search pipelines using embeddings and vector databases (Pinecone, FAISS, Chroma, Milvus).
• Integrate LLMs (OpenAI, Azure OpenAI, Gemini, Anthropic, HuggingFace models) into enterprise platforms.
• Implement prompt engineering, guardrails, and hallucination mitigation strategies.
• Design AI observability and evaluation frameworks to monitor model performance and reliability.
• Build event-driven AI architectures using Kafka, Redis Streams, or similar technologies.
• Deploy scalable AI infrastructure using Docker, Kubernetes, and cloud platforms.
• Collaborate with data engineers and backend teams to integrate AI services into production applications.

Required Qualifications

• 8+ years of software engineering experience with strong backend development.
• 4+ years of experience building AI/ML systems in production environments.
• Hands-on experience with Large Language Models (LLMs) and Generative AI architectures.
• Experience building Retrieval-Augmented Generation (RAG) systems.
• Strong expertise in Python and AI frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, or CrewAI.
• Experience with vector databases such as Pinecone, FAISS, Chroma, or Milvus.
• Experience designing microservices-based AI systems.
• Experience with cloud platforms such as AWS, Azure, or Google Cloud Platform.
• Experience with Docker, Kubernetes, and CI/CD pipelines for ML systems.
• Strong understanding of LLMOps / MLOps practices including model versioning, monitoring, and evaluation.

Preferred Qualifications

• Experience building multi-agent AI systems or autonomous workflows.
• Experience implementing AI evaluation frameworks, guardrails, and safety layers.
• Knowledge of event-driven systems using Kafka, Redis Streams, or RabbitMQ.
• Experience integrating AI systems with enterprise knowledge bases and structured data sources.
• Experience building AI systems with observability and human-in-the-loop workflows.