Open to opportunities

Narendra N

@narendran

Message

I build AI safety frameworks and production multi-agent LLM systems.

India

Message

What I'm looking for

I'm targeting AI safety, LLM systems, and multi-agent research roles where I can build adversarial benchmarks, evaluation pipelines, and reliable agentic systems.

I've built and published AI safety frameworks including ARGUS, a constitutional AI red-teaming framework, and SHADE, which evaluates covert coordination in multi-agent LLM systems. My research tests frontier models against principal hierarchy attacks, JSON tool-call injection, and steganographic collusion.

At Programmers Trend, I reduced Transformer inference latency by 10× and built RAG-based NLP chatbots that improved response accuracy by about 25%. I also independently shipped OpenHire, an AI job-application agent that scans 150+ career portals and dynamically tailors resumes using Mistral AI.

Experience

Work history, roles, and key accomplishments

Current

AI/ML Engineer (Part-Time)

Current

Programmers Trend

May 2025 - Present (1 year 4 months)

Reduced Transformer inference latency by 10x using knowledge distillation and model optimization in production pipelines. Built RAG-based NLP chatbot systems improving response accuracy by ~25% across 10K+ sample datasets.