I'm a senior software engineer with 10+ years of experience.
Today I focus on Agentic AI systems — multi-agent pipelines that do real-world research, forensic analysis, and automation, not just chat. I particularly love the engineering challenge of making LLM-powered systems reliable, not just impressive.
When I'm not shipping code, I teach high school mathematics and enjoy breaking down complex technical concepts into things anyone can understand.
🎯 My superpower: I can navigate between a low-level circuit diagram and a high-level LLM orchestration graph without losing context. Rare combo.
|
Multi-agent forensic accounting for Indian stocks Detects accounting irregularities, governance risks & value traps in NSE/BSE companies. Five parallel agents (Forensic, Management, RPT, Market Intelligence, Narrative) orchestrated via LangGraph, synthesized into a "Detective Story" report.
|
Daily autonomous research pipeline for special-situation investing Monitors NSE/BSE filings for insider trades & corporate events, then runs a 4-level deep-research pipeline (DeepSeek V3 + Qwen). Persists insights in PostgreSQL with
|
|
AI that reads your logs so you don't have to — at 3 AM Ingests production logs, clusters them with HDBSCAN, flags anomalies with Isolation Forest, investigates root causes via cross-encoder reranked RAG, and drafts fixes for human approval. Human-in-the-loop learning improves recommendations over time.
|
AI-powered drug information assistant A conversational tool for looking up medicines, active ingredients, and substitutes — built with a clean, fast React frontend and an intelligent backend that surfaces the right information quickly and safely.
|
PRs to projects I depend on. Sorted by repo stars, descending. (merged) = in upstream, (open) = in review.
- vercel/next.js
⭐140,097 —
fix 3 broken external guide links;fix 2 broken external guide links (Stack Auth, Chakra UI);fix 4 broken links in app router guides and example README;fix broken documentation links in examples and templates;honor pageExtensions in no-html-link-for-pages(open) - denoland/deno
⭐107,163 —
update Chocolatey install link to community.chocolatey.org;fix dead MDN link to Body interface(merged ✅) - fastapi/fastapi
⭐99,419 —
replace dead Uber Ludwig blog link with project repo in 14 translations(open) - vitejs/vite
⭐81,554 —
correct VoidZero announcement URL in announcing-vite6(merged ✅);fix broken Rolldown Plugin reference link in api-plugin.md(open);fix broken rolldown plugin options link in api-plugin.md(open);fix broken and malformed documentation links(open) (open) - OpenHands/OpenHands
⭐77,807 —
fix typo in OpenHands docs URL in add_agent.md(merged ✅) - withastro/astro
⭐60,321 —
remove dead llms.txt reference(merged ✅) - microsoft/autogen
⭐59,081 —
fix 2 broken external doc links (FAQ + Aspire dashboard)(open) - remix-run/react-router
⭐56,456 —
replace dead https://rmx.as/discord shortlink with https://discord.gg/reactrouter(open) - crewAIInc/crewAI
⭐54,011 —
correct broken MindsDB data_sources link in ai_mind_tool README;correct broken AWS IAM Roles link in aws/s3 README;correct broken Tavily Python SDK link in tavily_extractor_tool README;remove dead merge.dev/discord link in merge_agent_handler_tool README;correct broken Hyperbrowser SDK reference links;correct broken Parallel Processors link in parallel_tools README;correct broken Browserbase Live Debug link in browserbase_load_tool README;correct broken Stagehand reference link in stagehand_tool README(open) - BerriAI/litellm
⭐50,941 —
propagate ssl_verify through aiohttp handler + retry path (#30778);promote role=system in messages[] to top-level system param (#30705);fix 3 broken docs links (sigstore cosign + litellm enterprise);apply default_team_params.models to newly created teams;fix broken guardrails docs link in ibm_guardrails README;fix broken links in README and enterprise docs(open) - pixijs/pixijs
⭐47,442 —
remove dead https://pixijs.io/customize link in v7 migration guide(open) - pydantic/pydantic
⭐28,060 —
correct broken versioned version-policy link in HISTORY.md(open) - langchain-ai/langchainjs
⭐17,825 —
fix 4 broken external doc links(open) - mattermost/mattermost-mobile
⭐2,679 —
disable syntax highlighting and line numbers for code blocks without language;date separator missing day of month on certain Android devices(open) - lidatong/dataclasses-json
⭐1,483 —
respect default_factory for abstract generic fields in from_dict(open) - The-OpenROAD-Project/ORAssistant
⭐41 —
Fix 5 bugs: PDF crash, unused env var, missing state field, hardcoded model, typo;Fix 4 runtime bugs: crash, streaming None, discarded replace, memory leak(open)
- Building more reliable agentic systems (the harness matters as much as the model)
- Forensic accounting automation for Indian public markets
- Low-level systems — revisiting the ECE roots
- Value investing through the lens of AI-assisted research