My background spans NLP, knowledge graphs, fraud detection, and production ML.
I am interested in building self-improving AI systems that work with language and structured data. I’m exploring how feedback, reinforcement learning, and post-training can help these systems adapt and make better decisions. I’m also interested in making autonomous agents more reliable and efficient in production by understanding where they fail, evaluating their behavior, and improving performance over time.
Current Interests
- Post-training and reinforcement learning for language models
- Reward modeling and preference learning
- AI agents and autonomous workflows
- Evaluation of LLM behavior and reliability
- Applied ML systems for high-stakes domains
Published Work
Rajat Patel. (2023). InterosML @ Causal News Corpus 2023: Understanding Causal Relationships: Supervised Contrastive Learning for Event Classification
Rajat Patel, Francis Ferraro. (2020). On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling
Rajat Patel. (2020). Jointly Learning Knowledge Graph Embeddings, Fine Grain Entity Types and Language Models (Master thesis)
Writing
I write about reinforcement learning, post-training, LLM systems, and applied machine learning. Blog →