Assignment Description

We are seeking a Senior AI Engineer with expertise in Conversational AI and Knowledge Systems to lead the development of a scalable chatbot platform that integrates structured knowledge graphs with unstructured data from vector databases. The role involves LLM orchestration, backend development, and delivering a secure, high-performance system for 300+ concurrent users.

Working closely with a Knowledge Graph expert, the engineer will design and implement backend architecture to manage context and memory, optimize data retrieval, and establish monitoring to address issues in accuracy, latency, and cost. A strong focus on data security, role-based access control, and compliance is essential.

Key responsibilities also include testing, validating knowledge queries, implementing feedback loops, and managing infrastructure costs without compromising performance.

Required Qualifications:

• Extensive experience in LLM orchestration and conversational AI deployment
• Experience designing and implementing comprehensive monitoring and alerting solutions
• In-depth understanding of NLP and machine learning techniques for dialogue enhancement
• Hands-on knowledge of vector databases such as Pinecone or Weaviate
• Expertise in system scaling, performance tuning, and caching strategies
• Proven track record in optimizing infrastructure costs across cloud platforms (e.g., AWS, Azure)
• Strong backend engineering skills with a focus on chatbot memory and context handling