AI Software Engineer / RAG / LLM

A rapidly growing analytics and technology organization operating in data-intensive consumer markets is seeking an AI Engineer to join its applied intelligence team. This company is building next-generation AI systems that blend large-scale data assets with modern agentic workflows, retrieval-augmented generation (RAG), and LLM-driven automation to power real end-user products.

This role focuses on transforming complex business questions into production-ready AI tools, building retrieval pipelines, orchestrating decision flows, designing agent behaviors, and deploying AI systems that customers actually use. You'll work at the intersection of data engineering, product design, and intelligent automation in an environment where experimentation and iteration are core to the culture.

This is a full-time, hybrid role based in the Chicago Loop, offering an opportunity to shape foundational AI capabilities within a company where data is central to every product decision. Required Skills & Experience

• Meaningful hands-on experience developing applications with the LangChain ecosystem, including agents, tools, memory, and workflow components.
• Strong understanding of RAG architectures, vector databases, embedding strategies, and document ingestion pipelines.
• Prior experience building and deploying LLM-powered tools, chat flows, or agentic systems used by real customers or internal teams.
• Ability to design structured logic such as decision trees, routing strategies, workflow orchestration, and evaluation frameworks for AI behavior.
• Familiarity with AI UI/UX flows or operational tooling (e.g., Flowise, LangGraph, custom orchestration layers).
• Background working in data-heavy environments-ideally industries such as retail analytics, market intelligence, CPG, or similar (e.g., Nielsen, SPINS, IRI).
• Proficiency in Python and experience integrating AI systems with data pipelines, APIs, or backend services.
• Clear communication skills and the ability to collaborate in cross-functional product and engineering settings.

Desired Skills & Experience

• Experience fine-tuning or customizing LLM behavior through prompt engineering, retrieval tuning, or lightweight model adjustments.
• Exposure to vector databases such as Pinecone, Weaviate, Chroma, or Elasticsearch-based embeddings.
• Familiarity with evaluation frameworks, guardrails, and model monitoring techniques.
• Experience developing automation flows, agent handoffs, or multi-model orchestration stacks.
• Background contributing to ML ops tooling or AI platform infrastructure.
• A strong product mindset-comfort working in iterative cycles and shipping quickly.

What You Will Be Doing Tech Breakdown:

• 50% RAG pipeline development, agent/tool design, system architecture
• 30% workflow logic, decision modeling, evaluation, and iteration
• 20% cross-functional collaboration and product integration

Daily Responsibilities:

• Build and refine production-grade RAG pipelines, including ingestion, chunking, embedding, and retrieval logic.
• Develop intelligent agent workflows using LangChain, Flowise, or custom orchestration layers.
• Architect decision trees, rules-based logic, and routing frameworks that guide model behavior and improve reliability.
• Collaborate with product and data teams to translate high-level problem statements into deployable AI tools.
• Integrate AI components into backend services, APIs, and analytics workflows.
• Evaluate model outputs, run experiments, tune behavior, and implement guardrails to improve accuracy and safety.
• Stay current with emerging agentic frameworks, orchestration methodologies, and LLM capabilities-and bring new ideas into production.

The Offer You will receive the following benefits:

• Medical, dental, and vision coverage options
• Competitive salary
• Flexible work hours with a hybrid schedule in the Chicago Loop
• Significant opportunities for growth, experimentation, and ownership in shaping the AI roadmap

#LI-OP