- The resource should be able to design and implement solutions using Large Language Models (LLMs) using direct APIs to LLMs and via solutions such as Retrieval Augmented-Generation (RAG).
- The ideal resource is a strong developer that can optimize performance for latency, costs, concurrency, while maintaining high accuracy and high security. Should understand the structure of various backend systems such as authentication, authorization, enterprise databases, enterprise APIs, etc., in the context of an end-to-end solution.
- Should be able to collaborate with cross-functional Agile teams to deliver new functionality and use cases within the chatbot platform.
The candidate will work closely with stakeholders, tech-leads, and product owners on prioritized features.
- The candidate will work on designing solutions, develop code, and work with junior members on implementation details and code reviews
- Expertise in designing, developing, and deploying chatbot solutions.
- Experience in developing and consuming APIs that interact with LLMs.
- Should have strong backend programming skills in Python, expertise with AWS cloud environment, and experience in SQL.
- Fluency in core concepts of RAG, LLMs, and prompt engineering are required.
- Experience with prompt engineering with LLMs and an understanding of advantages/limitations of different LLMs.
- Experience with cloud environments such as AWS or Azure (AWS preferred).
- Fluency in core concepts of RAG, LLMs, and prompt engineering are required.
- Experience with traditional conversational AI platforms is a plus.
- Strong understanding of aspects such as concurrency, latency, and trade-offs between high accuracy, cost, and high security.
- Experience with end-to-end solution design to deployment process is a strong plus.
- Required Education : At least a Bachelor s Degree (or equivalent experience) in Computer Science, Software/Electronics Engineering, Information Systems or closely related field is required.
TBD