Harshit Purohit

• Graph Embeddings: Designed Attentive BPE; evaluated 10 benchmarks on H100 against SOTA. • LLM Retrieval: Reengineered Llama-3/Qwen into bidirectional retrievers (Look Both Ways). • Entity Linking: Built fine-tuning & Conformal Prediction pipelines scaled to 6M entities. • Track Record: Codebase & infra lead for 2 papers submitted to ACL & SEMANTICS 2026.

• Package Engineering: Maintained and optimized core open-source R packages (smoof, ecr2) for evolutionary computation. • Optimization Research: Conducted research in multi-objective optimization to drive data-driven package enhancements. • Reproducibility: Authored comprehensive documentation and functional guides to streamline onboarding and ensure research reproducibility.

• Analyzed company data to identify patterns and provide actionable business recommendations to stakeholders • Used Python to clean and integrate data into the company's database for future use • Collaborated with a team to deliver analysis reports based on the findings

• Built a conversational, multi-platform resume chatbot using Google's Dialogflow API and NLP techniques for B2C use cases • Designed intents, entities, training phrases, and contexts to drive the chatbot's conversational logic • Deployed the chatbot across Google Assistant, Facebook Messenger, Slack, and Telegram as part of a collaborative team