Full-Stack AI Engineer

Full-Stack AI Engineer – Remote AI Engineering | LLMs | Python | React | MLOps | Cloud Infrastructure Position Type: Full-Time, Remote Working Hours: U.S. Client Business Hours (with flexibility for sprint planning, deployments, and experimentation cycles) About the Role At Pavago , one of our clients is hiring a Full-Stack AI Engineer to design, build, and deploy production-ready AI applications that combine modern software engineering with applied artificial intelligence. This is a highly technical, hands-on role where you’ll build intelligent products from end to end—integrating Large Language Models (LLMs), machine learning models, vector databases, cloud infrastructure, and modern web applications into scalable production systems. You’ll collaborate closely with product managers, data scientists, and engineering teams to develop AI-powered solutions that automate workflows, improve user experiences, and create measurable business impact. If you’re passionate about shipping AI products—not just experimenting with models—this role is built for you. What You’ll Own AI Application Development Build and deploy AI-powered applications using modern software engineering best practices. Integrate LLMs and machine learning models into production environments. Develop intelligent features including: AI chatbots Semantic search Document intelligence AI copilots Workflow automation Build scalable APIs that expose AI capabilities to applications. LLMs, RAG & AI Integration Integrate models using: OpenAI Hugging Face PyTorch TensorFlow Build Retrieval-Augmented Generation (RAG) pipelines. Implement semantic search using vector databases including: Pinecone Weaviate FAISS ChromaDB Optimize prompt engineering and inference workflows. Monitor model accuracy, latency, and production performance. Data Engineering & AI Pipelines Build ETL pipelines for structured and unstructured data. Automate: Data ingestion Cleaning Validation Versioning Manage workflows using: Airflow Prefect D