Senior AI Engineer

IWConnect; Macedonia (OH); On-site; USD 120,000 - 150,000; Full time

Job summary

IWConnect is seeking a Senior AI Engineer who will own the complete development lifecycle, from architecture design to AI solution deployment. You will engage directly with clients to deliver production-grade AI applications and lead other engineers while ensuring high delivery quality.

The ideal candidate will have extensive experience in AI engineering, expertise in RAG systems, and proficiency in tools like Azure AI and LangChain. Join our dynamic team to make a significant impact in the AI space.

Qualifications

• 5+ years in software/AI engineering with hands-on delivery of production AI systems.
• Deep RAG expertise: chunking strategies, embedding models, and evaluation frameworks.
• Able to build production-grade code in Python, .NET, Java, or TypeScript.

Responsibilities

• Translate business problems into AI solutions and report progress clearly.
• Lead AI engineers and own delivery quality from PoC to production.
• Design end-to-end AI experiences and architect RAG pipelines.

Skills

AI development tools

Production-grade Python

RAG expertise

Client communication

Multi-step LLM workflows

Tools

Azure AI Foundry

AWS Bedrock

Google Vertex AI

LangChain

LangGraph

Job description

We're hiring a Senior AI Engineer who enjoys owning the entire development lifecycle. From shaping the architecture to building and deploying solutions, you'll use AI tools every day to work smarter and faster. You'll lead projects with minimal oversight, guide other engineers when needed, and confidently deliver independently while collaborating with experts for reviews and validation. Our team builds enterprise‑grade AI applications, including RAG systems, agentic workflows, and modern AI‑powered solutions.

What you'll do:

• Work directly with clients: translate business problems into AI solutions, explain how the technology behaves (and its limits), and report progress clearly;
• Support proposals and pre‑sales for new AI engagements;
• Lead AI engineers on engagements: if needed to have ability to set tasks, review work, give feedback, and support growth and performance;
• Own delivery quality and the path from PoC to production;
• Design end‑to‑end AI‑powered experiences and the systems behind them: model selection, deployment patterns, infrastructure;
• Architect and build RAG pipelines – chunking (semantic/recursive/hierarchical), embedding selection, retrieval, hybrid search, re‑ranking, and evaluation;
• Build agentic / multi‑step workflows (LangChain, LangGraph, or equivalent): multi‑agent designs, agent‑to‑agent protocols, and tool/API/MCP‑style integration with enterprise systems;
• Deploy on a hyperscaler AI platform (Azure AI Foundry, AWS Bedrock, Google Vertex AI, K8s based or equivalent);
• Build for production: observability, evaluations, AI safety, bias/failure‑mode handling, security, and cost control;
• Write the production code yourself – hands‑on;
• Use AI development tools (GitHub Copilot, Cursor, Claude Code, etc.) as part of how you build and validate what they produce.

Who are you:

• 5+ years in software/AI engineering, with substantial hands‑on delivery of production AI/LLM systems (not only PoCs or notebooks);
• Deep RAG expertise: chunking strategies, embedding models, vector databases, retrieval, re‑ranking, and evaluation frameworks;
• Strong with agentic / multi‑step LLM workflows and orchestration (LangChain, LangGraph, or equivalent) and tool/API integration;
• Able to build real software – production‑grade code in at least one of Python, .NET / C#, Java, or Node.js / TypeScript (APIs, services, integrations);
• Experience deploying AI workloads on at least one hyperscaler AI platform;
• Solid on production concerns: observability, evaluation, safety, security, cost;
• Daily, fluent use of AI development tools in your own work;
• Proven ability to take an AI solution from idea to production independently;
• Confident client‑facing and team communication;
• Knowledge graphs and graph‑based retrieval (Neo4j, RDF/SPARQL, GraphRAG);
• NL2SQL, semantic layers, intelligent document processing;
• LLMOps/MLOps tooling and practices.

Nice to have:

• Broad / multi‑stack traditional software‑engineering background;
• Experience with large, regulated organisations (banks, insurers, government, utilities);
• Relevant certifications;
• Formal team‑leadership/performance‑management experience.