LLM Application Engineer in New York

Job Description

\n
• Design, develop, and deploy applications powered by Large Models (LLMs).

\n

• Build and optimize RAG (Retrieval-Augmented ) pipelines using vector databases and embedding models.

\n

• Integrate LLMs such as GPT, Claude, Gemini, Llama, and other foundation models into production applications.

\n

• Develop AI agents, chatbots, copilots, and intelligent automation solutions.

\n

• Engineer effective prompts and implement structured output, function calling, and tool-use workflows.

\n

• Fine-tune and evaluate LLMs for specific business use cases and improve accuracy, relevance, and reliability.

\n

• Work with Python, APIs, LangChain/LangGraph, vector databases, and cloud AI platforms.

\n

\n

\n

Qualifications

\n

\n

\n
• Bachelor’s degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Information Technology, or a related field.

\n

• Strong coding in a variety of and technical communication skills

\n

• Strong programming skills in Python.

\n

• Knowledge of Machine Learning, Deep Learning, NLP, and Generative AI.

\n

\n