Responsibilities of the Candidate:

Assist in the design and deployment of efficient vector databases to support large-scale Generative AI projects.
Support the development and enhancement of Retrieval-Augmented Generation (RAG) pipelines for robust information retrieval and text generation.
Help integrate the PydanticAI or any other Agentic frameworks and implement context-aware techniques for Generative AI models.
Contribute to the creation and management of human-in-the-loop workflows to ensure output accuracy, control, and bias mitigation in Generative AI applications.
Monitor and evaluate Generative AI model performance, assisting in addressing potential biases and fairness concerns.
Apply prompt engineering techniques to refine model interactions and improve the quality of outputs.
Utilize statistical and machine learning methods to analyze and prepare data for Generative AI projects.
Stay updated on the latest advancements in Generative AI and related fields (e.g., Natural Language Processing, Deep Learning).
Communicate technical concepts clearly to both technical and non-technical stakeholders.
Collaborate effectively with cross-functional teams (engineering, research, product) to deliver impactful Generative AI solutions.

Requirements:

Some experience or academic knowledge in building and optimizing Generative AI models (e.g., LLMs, RAG pipelines, fine-tuning).
Basic understanding of vector databases and their use in Generative AI.
Familiarity with prompt engineering techniques.
Proficiency in Python programming and exposure to relevant AI frameworks (e.g., TensorFlow, PyTorch).
Solid foundation in statistics, machine learning, and data analysis.
Strong analytical and problem-solving abilities.
Good communication and teamwork skills.
Relevant internship experience or academic projects in AI/Data Science roles is a plus.