Build a chatbot system from the ground up using cutting-edge large language models and Retrieval-Augmented Generation (RAG) techniques.
Requirements
- Built a production-grade chatbot or generative AI system from scratch
- 8–10+ years of experience in machine learning or AI, with deep NLP/LLM exposure
- 2+ years of applied experience with LLMs and RAG pipelines
- Strong hands-on skills in Python, API development, and debugging large-scale ML systems
- Proven experience with transformer-based architectures
- Familiarity with DevOps workflows and monorepo codebases
- Experience with cloud-based ML deployment, ideally in AWS (SageMaker, Bedrock)
Responsibilities
- Design and deploy chatbot capabilities end-to-end using LLMs and RAG architecture
- Architect multi-component workflows for semantic search, hallucination mitigation, and prompt engineering
- Train, fine-tune, and optimize LLMs (e.g., GPT-4, Claude, BERT, RoBERTa, T5) using modern frameworks
- Own code from prototype through production in monorepo environments with CI/CD pipelines
- Deploy and monitor solutions in AWS (preferred) or Azure
Other
- Remote (U.S.-based candidates; Raleigh/Durham location is a plus)
- 6-month+ W2 Contract (potential to extend up to 18 months)
- Collaborate cross-functionally with engineers, product managers, and AI/ML teams
- Master’s or PhD in Computer Science, AI, Applied Math, or related field
- Background in legal tech, healthcare, or domain-specific chatbot use cases
