Description
You will design and implement AI-powered features and applications integrating large language models with scalable backend systems.
Responsibilities
- Design and develop AI applications using Python and Java.
- Integrate OpenAI and Azure AI services using Retrieval-Augmented Generation (RAG) architecture.
- Manage embeddings and semantic search using vector databases like Pinecone, Weaviate, or Chroma.
- Build and maintain APIs, microservices, and ETL pipelines to connect AI models with other systems.
- Collaborate with data scientists to deploy machine learning models and define performance metrics.
Required Skills
- 5+ years of professional experience in software development.
- Proficiency in Python and Java.
- Hands-on experience with OpenAI GPT models and Azure AI services.
- Experience with vector databases (Pinecone, Weaviate, or Chroma).
- Solid understanding of SQL and NoSQL databases.
- Experience building ETL pipelines and integrating data via RESTful APIs.
- Knowledge of data architecture and modeling for scalable microservices.
- Proficiency with Git for version control.
- Ability to define data validation rules and monitor AI model performance metrics.
Preferred Skills
- Experience with agile project management practices.
- Ability to write technical documentation for API integrations and data pipelines.