Role: AI Engineer

Location: DE, OH & TX(Onsite)

Contract

Job Description:

AI Engineer specializing in RAG (Retrieval-Augmented Generation) and Agentic AI designs, builds, and deploys autonomous systems and smart retrieval pipelines. They create goal-driven workflows that allow Large Language Models (LLMs) to reason, use external tools, collaborate in multi-agent networks, and securely access enterprise knowledge. 

Key Responsibilities

• Agentic Workflow Design: Build single- and multi-agent systems capable of autonomous planning, multi-step reasoning, execution loops, and tool/function calling. 
• RAG Pipeline Development: Construct scalable retrieval systems using data chunking, embeddings, hybrid semantic/keyword search, and re-ranking techniques to ground AI responses. 
• Model Integration: Integrate commercial and open-source LLMs (such as OpenAI, Claude, Llama, and Gemini) into robust backend microservices and REST APIs. 
• System Optimization: Tune inference latency, token usage, reliability, and infrastructure costs across cloud services (AWS, Azure, or GCP). 
• LLMOps & Evaluation: Implement testing harnesses, guardrails, and observability tools to track agent performance, prevent hallucinations, and audit outputs. 

Required Skills & Qualifications

• Programming: Strong proficiency in Python (and optionally TypeScript/Node.js) for building scalable microservices and data pipelines.
• Orchestration Frameworks: Hands-on experience with tools like LangChain, LangGraph, CrewAI, AutoGen, or LlamaIndex.
• Vector Databases: Experience managing and querying vector stores such as Pinecone, Weaviate, Milvus, Qdrant, or Chroma.
• Software Engineering Fundamentals: Solid background in building production-grade asynchronous APIs, database management (SQL/NoSQL), and cloud deployments.