LLM Engineer – OpenAI & LangChain
Drive cutting-edge AI innovation in the insurance industry as an LLM Engineer. Use OpenAI, LangChain, and Azure to build scalable, production-ready Generative AI systems. Work on advanced RAG pipelines and agentic workflows in a hybrid setup. Strong coding and real-world deployment skills are key.
What is in it for you:
• Salaried: $60-75 per hour.
• Incorporated Business Rate: $75-90 per hour.
• 5-month contract with the potential for permanent employment.
• Full-time position: 37.50 hours per week.
• Weekday schedule from 9 am to 5 pm.
• Hybrid work: in-office Tuesday to Thursday.
Responsibilities:
• Design, build, and deploy LLM-powered applications using OpenAI APIs, LangChain, and related frameworks.
• Develop Retrieval-Augmented Generation (RAG) pipelines, agentic workflows, and chatbot systems.
• Fine-tune and optimize LLMs to support business use cases with minimal hallucinations.
• Apply prompt engineering and evaluation techniques to improve model outputs.
• Integrate solutions with Azure, Databricks, Azure Cognitive Search, and VectorDBs (FAISS, Pinecone).
• Collaborate cross-functionally to scope, prototype, and productionize AI systems.
• Employ LLMOps and MLOps practices for deployment, monitoring, and lifecycle management.
• Stay up to date on trends in GenAI, LLMs, and open-source tools.
What you will need to succeed:
• Bachelor's degree in computer science, computer engineering, or a related technical field.
• Proficiency in Python and related libraries.
• 2+ years of hands-on experience in NLP, LLMs, and Generative AI.
• Strong understanding of prompt engineering and LLM fine-tuning.
• Experience with OpenAI APIs, LangChain, and Retrieval-Augmented Generation (RAG) architectures.
• Working knowledge of Model Context Protocol (MCP) and its application in LLM systems.
• Experience with cloud platforms such as Azure (preferred), AWS, or GCP.
• Hands-on experience with Databricks and Azure Cognitive Search.
• Familiarity with Vector Databases (e.g., FAISS, Pinecone, Weaviate) and agent frameworks (e.g., Autogen).
• Experience with DevOps/MLOps tools such as Git, Docker, MLflow, and Kubernetes.
• Strong communication skills with the ability to translate technical concepts into business value.
• Nice to have: Experience with Streamlit, Flask, or JavaScript for building interactive frontends.
Why Recruit Action?
Recruit Action (agency permit: AP-2504511) provides recruitment services through quality support and a personalized approach to job seekers and businesses. Only candidates who match hiring criteria will be contacted.
# MFCJP00015284