AI Engineer · Builder · Bangalore
I build systems at the intersection of language models and real-world utility - from evaluation frameworks and agent pipelines to tools that make AI actually work in production. Currently exploring agent memory, multi-agent orchestration, and the infra that makes large systems reliable.
agent-event-protocol · JavaScript
Open observability protocol for AI agent systems - structured event capture, real-time session tracing, and multi-agent workflow visibility in a single self-hosted deployment.
claude-code-for-ai-engineers · Python
A methodology-first skill pack for AI engineers - covering RAG evaluation, agent debugging, MCP servers, paper reproduction, and benchmark reporting.
agent-workflow-comparison · Python
A controlled benchmark of 10 AI agent workflow patterns - single-step through human-in-the-loop - evaluated across 25 tasks on success rate, answer quality, tool accuracy, latency, and token cost. Results are directly comparable.
cartograph · Python
Intelligent mapping and data visualization.
Python · TypeScript · JavaScript
LangChain · OpenAI · Anthropic Claude · Hugging Face
FastAPI · PostgreSQL · Docker
I work at the edge of what language models can reliably do - building the scaffolding, the evals, and the debugging tools that make the difference between a demo and a system. My interest is both in the models themselves and but more in the engineering discipline around them.
Bangalore, India