About:

• Location: Austin, TX
• Contract: 6 months

The Role:

• Develop pipelines to parse documents, chunk, vectorize, and persist vector stores
• Design vector store schemas
• Develop prompt templates with various prompt engineering techniques to interact with LLMs
• Experience in prompting with few-shot examples
• Develop semantic agents and interfaces between the agents
• Develop microservices and expose them as APIs
• Collaborate with architects and full-stack developers to deliver generative AI solutions
• Implement best practices for data management and model deployment
• Ensure the scalability and performance of generative AI solutions

Qualifications:

• Bachelor’s degree and 10+ years of experience required.
• Designed and developed scalable generative AI platforms and frameworks to accelerate enterprise use case development.
• Built end-to-end pipelines for document parsing, intelligent chunking, vectorization, and storage in vector databases (e.g., FAISS, Pinecone, Chroma).
• Created and optimized vector store schemas to support efficient semantic retrieval and RAG-based applications.
• Developed prompt templates using advanced prompt engineering techniques, including few-shot and zero-shot prompting.
• Engineered semantic agents and built interfaces for agent collaboration and orchestration in LLM-powered workflows.
• Built and deployed microservices exposing LLM capabilities through scalable APIs.