AI Model Developer- LLM,RAG – [REMOTE] Position Available In Monmouth, New Jersey

AI Model Developer- LLM,RAG – [REMOTE] Centstone Hazlet, NJ 07730 •

Remote Job Title:

AI Model Developer Location:

[Remote]

Job Summary:

We are looking for a skilled and innovative AI Model Developer to join our team. The ideal candidate will have hands-on experience with Large Language Models (LLMs), particularly OpenAI and Azure OpenAI, to develop advanced AI solutions. This role involves building, fine-tuning, and deploying AI models that improve performance and user experience.

Key Responsibilities:

Develop and implement AI models using OpenAI’s ChatGPT API or similar LLMs, with a focus on prompt engineering and fine-tuning. Leverage retrieval-augmented generation (RAG) techniques for enhanced performance and retrieval capabilities. Write Python scripts for data processing, model deployment, and API integration. Integrate AI solutions with RESTful APIs and third-party services (e.g., OpenAI). Manage structured and unstructured data using SQL and MongoDB. Use Azure Databricks for data processing and model training. Implement embedding models for efficient vector storage and retrieval. Work with distributed data systems such as Databricks and Apache Spark. Troubleshoot AI model issues and debug system integrations. Conduct clustering, embedding creation, and evaluation for various data types. Apply model alignment and bias mitigation strategies. Document processes, changes, and system designs for traceability. Evaluate embeddings, retrievers, and generation models using tools like LangSmith and MLFlow.

Required Qualifications:

Experience with OpenAI’s ChatGPT API or similar LLMs, including Azure OpenAI for generation and embeddings. Familiarity with fine-tuning LLMs and prompt engineering, especially within Azure OpenAI. Proficiency in Python for scripting, data processing, and integration tasks. Experience working with APIs (OpenAI, RESTful APIs). Strong SQL skills and experience with MongoDB, including vector storage/indexing. Experience with vector databases such as Pinecone and FAISS . Knowledge of databases like Redis, SQL Server, and MongoDB. Experience with embedding models for vector data retrieval. Solid debugging and integration troubleshooting skills. Strong problem-solving and analytical thinking. Excellent documentation practices for tracking changes and system designs. Familiarity with LangChain and LangGraph frameworks. Hands-on experience with Pinecone for vector storage and retrieval.