LLM & GenAI Engineer — Production-Grade AI Pipelines

Latitude; Chicago, Northern (IL, KY); Hybrid; USD 140,000 - 210,000; Full time

Job summary

Latitude in Chicago is seeking a Senior AI Platform Engineer who has moved beyond basic prompting to build production-grade AI systems. You will own complex components of the core AI platform and collaborate with applied scientists, backend engineers, and enterprise stakeholders to deliver scalable generative AI applications.

You will design end-to-end RAG pipelines, optimize vector database integrations, and develop evaluation frameworks, while writing robust Python code and participating in

Qualifications

• 3–6 years of software engineering experience with 2+ years in LLMs and production systems.
• Hands-on experience with retrieval-augmented generation and fine-tuning.
• Experience with AI tooling and model deployment in cloud environments.

Responsibilities

• Design and implement end-to-end RAG pipelines and retrieval architectures.
• Build and optimize vector DB integrations for production-scale search.
• Develop LLM evaluation frameworks and automated regression tests.
• Conduct instruction fine-tuning and parameter-efficient fine-tuning (LoRA/QLoRA) on domain data.
• Write clean, observable Python code and participate in architecture reviews.

Skills

Python development

Asynchronous programming

RESTful API design

Cloud infrastructure

LLM orchestration (LangChain/LlamaIdx)

Vector databases

Distributed systems

Benchmarking/evaluation

Tools

LangChain

LlamaIndex

Pinecone

Weaviate

pgvector

Job description

Latitude in Chicago is seeking a Senior AI Platform Engineer who has moved beyond basic prompting to build production-grade AI systems. You will own complex components of the core AI platform and collaborate with applied scientists, backend engineers, and enterprise stakeholders to deliver scalable generative AI applications.

You will design end-to-end RAG pipelines, optimize vector database integrations, and develop evaluation frameworks, while writing robust Python code and participating in