QuadSci.ai is a leading AI product and orchestrated performance system for B2B Software companies. The Principal Generative AI Systems Engineer will be responsible for designing, developing, and deploying applications that leverage generative AI models, working closely with various teams to ensure seamless functionality and performance of AI applications.
Responsibilities:
- Design, configure and optimize the GenAI-tech stack including: LLM, Vector DB, Encoder / Decoder, prompt framework (ex. DSPy) and supporting cloud compute and service resources
- Design and implement RAG pipelines that enhance generative AI models by integrating external data sources
- Architect and engineer efficient retrieval systems that can fetch relevant data from databases, knowledge graphs, or external APIs to augment AI-generated responses
- Develop prompting pipelines that leverage context and retrieved information to generate accurate and contextually relevant responses
- Collaborate with machine learning engineers to implement advanced techniques such as vector search, semantic search, and embeddings to improve data retrieval accuracy
- Build and maintain robust pipelines for data retrieval, preprocessing, and integration into the generation process
- Implement automated testing frameworks to validate the performance of RAG and prompting pipelines
- Ensure that the retrieval and generation pipelines are scalable, reliable, and maintainable
- Continuously monitor and refine pipelines to improve efficiency and reduce latency
- Implement monitoring, logging, and alerting to maintain system health and uptime
- Collaborate with cross-functional teams including UX/UI designers, product managers, and DevOps engineers to deliver high-quality products
- Collaborate with DataML Engineers, Integration Engineers & GenAI Engineers for customer-specific deployments & configurations
- Write clean, maintainable code and conduct code reviews
- Document technical architecture, processes, and best practices