Prompt Engineer / LLM Specialist

Title: Prompt Engineer / LLM Specialist

Location: New Jersey, New York (Hybrid)

Type: Contract

Role Summary

• The Prompt Engineer / LLM Specialist designs, builds, and optimizes LLM-powered systems. This role goes beyond prompt writing to include hands-on Python development, model behavior analysis, and applied AI modeling, with a focus on building reliable, high-quality, production-ready LLM solutions.
• Prompt Engineer/LLM Specialist - Support & Innovation - Qty (1) - Design and update prompts, build RAG systems, optimize LLM performance.

Key Responsibilities

• Design, test, and refine prompts for LLM-based applications using systematic evaluation
• Develop Python-based pipelines for prompt experimentation, scoring, and iteration
• Build and optimize retrieval-augmented generation (RAG) systems, including indexing, retrieval, and reranking
• Analyze and tune model behavior using quantitative and qualitative evaluation methods
• Implement LLM orchestration logic, chaining, and tool usage in Python
• Collaborate with AI researchers and engineers to integrate modeling improvements
• Monitor LLM performance, drift, and failure modes in production environments
• Document prompt strategies, evaluation results, and best practices

Qualifications

• 4+ years of experience in AI, ML, NLP, or applied modeling roles
• Strong Python programming experience, including building reusable libraries and pipelines
• Solid understanding of machine learning and NLP fundamentals, not just prompt usage
• Hands-on experience working with LLMs, embeddings, and vector search
• Experience designing and evaluating RAG pipelines and model-assisted retrieval systems
• Familiarity with model evaluation, fine-tuning concepts, and inference optimization
• Experience deploying or supporting production AI/LLM systems preferred