Conduct a systematic review on RAG, LLMs, and semantic governance
Conduct benchmarking of enterprise and market solutions for DataOps automation
Develop embeddings engineering, chunking, and indexing techniques
Build and validate the vector database and retrieval mechanisms
Implement a RAG baseline, evaluating top-k, accuracy, and latency
Expected outcome: functional vector DB, RAG baseline meeting minimum metrics, and complete technical documentation.

Requirements

Master's degree in Exact Sciences, Computer Engineering, Computer Science, Statistics, Physics, or Applied Mathematics
Proficiency in Python programming
Knowledge of NLP, embeddings, and vector databases
Experience with PyTorch/TensorFlow
Understanding of data structures and analytical pipelines
Experience with RAG and LlamaIndex (preferred)
Academic publications (preferred)

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

PythonNLPembeddingsvector databasesPyTorchTensorFlowdata structuresanalytical pipelinesRAGLlamaIndex

Certifications

Master's degree