Senior AI & Full-Stack Software Developer – Remote

We are seeking an experienced AI-Focused Full-Stack Developer to architect, build, and deploy intelligent software applications. This role combines full-stack web development with modern AI capabilities, including RAG pipelines, AI agents, LLM integrations, and AI-driven automation. The ideal candidate can turn business workflows into scalable, AI-powered web applications and communicate complex technical concepts clearly. Key Responsibilities - Integrate OpenAI (GPT-4o), Anthropic (Claude), open-source LLMs, and other APIs - Build RAG systems, autonomous AI agents, and workflow automations using LangChain, LlamaIndex, CrewAI, or similar tools - Work with relational databases such as PostgreSQL/MySQL and vector databases such as Pinecone, Qdrant, Supabase pgvector, or similar - Develop responsive front-end applications using React, Next.js, or Vue - Build robust back-end APIs using Python/FastAPI/Flask, Node.js, or TypeScript - Optimize prompts, model performance, API costs, and database queries - Participate in Agile workflows, daily stand-ups, Git workflows, testing, and project updates through Slack and Jira/Asana. Requirements - 4+ years of software engineering experience - 1.5+ years of hands-on experience building production applications using AI models and LLMs - Hands-on experience with LangChain, LlamaIndex, or LLM API tool calling/function execution - Experience with vector databases such as Pinecone, Chroma, Supabase (pgvector), or Weaviate - Strong understanding of prompt engineering, function calling, agentic loops, and model evaluation - Strong proficiency in Python (FastAPI, Django) or TypeScript/Node.js - Experience with React.js, Next.js, or Vue.js - Experience with Git, GitHub/GitLab, Vercel, Docker, AWS, or GCP - Dedicated quiet home office, fiber-optic internet (minimum 100 Mbps), secondary backup connection, and power solution Preferred Qualifications - Experience with human-in-the-loop workflows, automated data extraction/OCR, or AI voice/chat assistants - Knowledge of local AI deployment or model fine-tuning using PyTorch/Hugging Face - Experience with serverless architectures or microservices on AWS/Google Cloud Role Details - Schedule: Monday–Friday, 9:00 AM–5:00 PM EST - Hours: Full-Time, 40 hours/week - Location: Remote