Job Title: AI Developer / Machine Learning Engineer Location: Hybrid (Chicago, IL) Duration: 6+ months Overview: We are seeking an experienced LLM Software Engineer to join a high-impact AI/ML team at a leading financial institution. The ideal candidate will bring a strong background in Python or Java development and hands-on experience building applications powered by Large Language Models (LLMs). You’ll work on next-gen intelligent systems using advanced AI tools and frameworks in a production-grade, cloud-native environment. Key Responsibilities: • Design, develop, and deploy production-grade systems using Python or Java. • Build and fine-tune applications utilizing LLMs such as OpenAI, LLaMA, Mistral, or Anthropic. • Develop Retrieval-Augmented Generation (RAG) pipelines using vector databases like Pinecone, Weaviate, or Milvus. • Implement and optimize LLM applications in AWS or Azure, focusing on scalability, API development, observability, and security. • Evaluate model performance through custom evaluation sets, human-in-the-loop feedback, and tools such as Promptfoo or Ragas. Requirements: • 7+ years in software development with a focus on Python or Java. • 2+ years of LLM-based application development experience. • 1+ year building RAG pipelines using vector search technologies. • Hands-on experience deploying LLM workloads in a cloud-native environment (AWS or Azure). • Deep understanding of LLM evaluation strategies and performance benchmarks. Additional Notes: • C2C is not allowed – candidate must be able to work on W2. • Role is hybrid, and candidates must be local to Chicago.