Description

You will design and implement production-ready chatbot systems using state-of-the-art LLMs. You will own the RAG architecture, fine-tuning processes, and client-facing user experiences for scalable AI deployments.

This role is on-site.

Responsibilities

• Build and optimize Retrieval-Augmented Generation (RAG) architecture for knowledge-intensive applications.
• Develop conversation management systems with context retention and memory for AI-powered chatbots.
• Fine-tune large language models for domain-specific tasks and implement multi-modal generative AI solutions.
• Design robust APIs for application integration and leverage cloud platforms for scalable deployment.
• Implement CI/CD practices and advanced prompt engineering strategies.

Required Skills

• 8+ years of experience applying AI to practical uses, including 2+ years in senior or lead roles.
• Proficiency in Python and JavaScript/TypeScript with a focus on AI/ML development.
• Deep knowledge of open-source tools like LangChain, TensorFlow, PyTorch, or Hugging Face.
• Experience with REST API development, NoSQL database design, and RDBMS design/optimizations.
• Familiarity with cloud LLM platforms (AWS Bedrock, Google Vertex AI, Azure OpenAI services).
• Hands-on expertise in chatbot design and delivering client-facing user experiences.
• Knowledge of Vector and graph databases.

Key Skills

Education

Bachelor's degree