LLM Engineer

Job Title LLM Engineer Location Dallas, TX (Onsite) Start Immediate Role Overview We are looking for a Senior Full Stack AI Engineer with strong experience in building scalable applications and integrating Large Language Models (LLMs). This role requires hands‑on expertise across backend, frontend, and cloud, along with the ability to deliver production‑grade AI solutions. Key Responsibilities Design and develop full‑stack applications using Java and React Build and integrate LLM-powered solutions using APIs (OpenAI, Claude, Azure OpenAI, etc.) Develop scalable microservices and REST APIs Deploy and manage applications on AWS or Azure Work with SQL and NoSQL databases for high‑performance applications Implement RAG, embeddings, and vector‑based search solutions Ensure security, performance, and reliability of applications Mentor junior developers and contribute to code quality and best practices Required Skills 10+ years of full‑stack development experience Strong expertise in Java (Spring Boot, Hibernate) Experience with ReactJS and modern frontend development Hands‑on with cloud platforms (AWS or Azure) Experience integrating LLMs (e.g., OpenAI API, Azure OpenAI Service, Amazon Bedrock, Claude) Knowledge of RAG, embeddings, and vector databases Strong database experience (SQL + NoSQL) Proficiency in Python for backend or data processing Experience with REST APIs and microservices architecture Understanding of security (OAuth2, JWT, OpenID Connect) Nice to Have Experience with Palantir Foundry Exposure to frameworks like LangChain, LlamaIndex, or Hugging Face Experience in enterprise AI/ML solution development #J-18808-Ljbffr First Soft Solutions LLC