Dr. Omar Khattab
Stanford NLP Postdoctoral Scholar
Sources checkedPostdoctoral NLP Scholar at Stanford University under Christopher Manning and Matei Zaharia. Creator of the DSPy framework for programmatic LLM pipelines and the ColBERT efficient late-interaction retrieval architecture. Pioneer in compounding AI systems and declarative prompt optimization.
Areas of focus
Professional niches
Proof of Work
ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
Invented ColBERT, a neural retrieval model utilizing late interaction over token-level representations rather than collapsing documents into a single dense vector, achieving cross-encoder retrieval quality with millisecond vector search latency.
Multi-vector token index storage requires larger RAM and disk allocations than single-vector embedding stores unless aggressive centroid quantization (ColBERTv2 / PLAID) is applied.
Context: Token-level BERT embeddings, MaxSim operator, PLAID index compression.
View missionDSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
Authored the DSPy Assertions paradigm, introducing computational assertions and suggestions directly into declarative LM graphs, enabling pipelines to self-correct upon constraint failure without manual prompt rewriting.
Backtracking loops require hard iteration ceilings to avoid infinite retry loops when models encounter unresolvable logical contradictions.
Context: Dynamic backtracking execution graph in Python, automated metric validation.
View mission