Pranav Purathepparambil

About

Built a production LLM-powered analyst assistant at Discern Security to speed up SOC investigations using a RAG pipeline over security vendor documentation (Python PDF ingestion, vector search). Demonstrates deep, security-critical LLM engineering: structure-aware chunking with custom table parsing, grounded/cited responses, prompt-injection defenses, and post-generation validation, validated via golden datasets and adversarial testing; tool is used daily by analysts.

Experience

Education

Key Strengths

• Built and deployed a production RAG system for SOC investigations
• Improved retrieval quality via structure-aware chunking and custom PDF table parsing
• Designed security-critical LLM guardrails (grounded prompting, citations, prompt-injection defenses, post-gen validation)
• Strong evaluation discipline (golden datasets, adversarial cases, component unit tests, end-to-end tests, retrieval metrics, latency checks)
• Pragmatic model/retrieval selection based on stakes, latency, and grounded behavior
• Effective collaboration with non-technical SOC stakeholders through iterative live demos and workflow alignment