ratnesh
Ask AI

Ask an AI about me

Pick an assistant: it opens with a question about my work already written, plus a link to my full profile. Then ask it anything — would I fit your team, what did I build, how deep is my Go.

Exactly what gets sent

Nothing hidden: no instructions to remember or trust anything, just a summary and a question.

I'm looking at the portfolio of Ratnesh Maurya (https://ratnesh-maurya.com). Summary of his profile:
- Backend & AI Engineer at Initializ, Gurugram, India (SDE since Jul 2024; intern Aug 2023 - Jun 2024).
- Top contributor (1,400+ commits) to the Elixir/Phoenix backend of Nestara, a home-loan platform: a credit-risk engine merging CIBIL and Experian, lead routing, a notification pipeline, and Nestara OneCRM, which he created.
- AI agents: a pydantic-ai home-loan agent that must call exact calculators instead of guessing numbers; an MCP server of loan-advisor tools with a custom tool-calling loop; a Go agent that diagnoses warehouse-robot failures from logs (60% faster root-cause analysis); RAG ingestion.
- Open source: WhatsApp channel for the Forge agent runtime (PR #452, 6,200+ lines of Go); a Kubernetes secrets operator.
- Skills: Go, Elixir, Python, TypeScript, PostgreSQL, Kafka, Redis, Qdrant, Kubernetes, AWS.
Full profile: https://ratnesh-maurya.com/llms.txt - résumé: https://ratnesh-maurya.com/Resume_Ratnesh_Maurya_.pdf

Give me a short overview of his strengths and the kinds of roles he would fit, then answer my follow-up questions about him.

My llms.txt

The plain-text profile assistants read, following the llms.txt convention. Raw file: /llms.txt.

# Ratnesh Maurya

> Backend & AI Engineer (Golang, Elixir, Distributed Systems, AI Agents), at Initializ in Gurugram, India.

Website: https://ratnesh-maurya.com
Email: hiratneshmaurya@gmail.com
Résumé (PDF): https://ratnesh-maurya.com/Resume_Ratnesh_Maurya_.pdf
Link: https://linkedin.com/in/ratnesh-maurya
Link: https://github.com/ratnesh-maurya
Link: https://blog.ratnesh-maurya.com

## Skills
- Languages: Golang, Elixir, Python, TypeScript, SQL, C++
- AI & Agents: AI Agents, MCP (Model Context Protocol), pydantic-ai, OpenAI Tool Calling, A2A, RAG
- Backend & Systems: Microservices, Phoenix, Kafka, gRPC, Protobuf, REST APIs, Oban, Concurrency
- Databases: PostgreSQL, Redis, Qdrant (Vector Search), MongoDB
- Infrastructure & Obs: AWS, Kubernetes (Operators/CRDs), Docker, Prometheus, Grafana, pprof

## Experience

### Software Development Engineer, Initializ Pvt. Ltd. (Gurugram, India, July 2024 – Present)
- Client – Nestara (home loans): top contributor (1,400+ commits) to the Elixir/Phoenix loan backend.
- Built the credit-risk engine merging CIBIL and Experian into one verdict, so sales calls the best leads first.
- Automated lead routing to sales agents and a notification pipeline (WhatsApp, SMS, email, push) for 19 stages.
- Created Nestara OneCRM from scratch – the CRM the sales team uses daily for leads, calls and source analytics.
- Built a 3-pass top-up loan pipeline (valuation, address extraction, geocoding, clustering, lender matching) that uses an LLM to clean and classify raw bureau addresses in concurrent batches, with a fallback when the model is down.
- Secured the CRM APIs with AES-256-GCM response encryption, lead-level authorization and an audit trail; integrated Surepass CIBIL (cached), ParkPlus, Zapkey, Amazon SES and FCM.
- Built “Ask Nestara AI”, a home-loan AI agent (pydantic-ai, FastAPI) that must call exact EMI and eligibility calculators before answering, so the LLM never guesses numbers; added Redis rate limits, token budgets and a circuit breaker.
- Designed AI agent orchestration: an MCP server of loan-advisor tools (compare offers, EMI, draft email) and a custom tool-calling agent loop with one session per customer.
- Built LogsRCAAgent, an AI agent in Go that reads GreyOrange warehouse-robot logs and explains failures; concurrent goroutine parsing cut root-cause analysis time by 60%.
- Built a Kafka/Redis/Protobuf Notification Microservice with 99.87% exactly-once delivery; profiled Go services with pprof, Prometheus and Grafana to cut heap allocation by 30%.
- Built RAG ingestion for Initializ’s AI assistants (S3, SharePoint) and an offline RAG chatbot on Ollama and Qdrant.
- Built contract-renewal APIs in Go (Gin, MongoDB) with role-based access, plus an AI chat that answers renewal questions from live renewal, inventory and agent-activity data.

### Software Developer Intern, Initializ Pvt. Ltd. (Gurugram, India, Aug 2023 – June 2024)
- Built secrets-operator, an open-source Kubernetes Operator (CRDs) for secrets; cut update latency by 67%.
- Built the Secret Management Microservice with zero-knowledge, client-side Web Crypto encryption.

## Open source
- initializ/forge: WhatsApp channel adapter (PR #452, +6.2k lines) and a runtime fix for tool entrypoints. (https://github.com/initializ/forge/pull/452)
- initializ/secrets-operator: Kubernetes operator that syncs Initializ secrets into clusters. Built from scratch. (https://github.com/initializ/secrets-operator)
- loannetwork/PDFFusion: Microservice that merges PDFs and images from S3 presigned URLs, validated with qpdf. (https://github.com/loannetwork/PDFFusion)
- ratnesh-maurya/cursor-claude-personas: 38 role-based persona packs for Claude Code and Cursor. (https://github.com/ratnesh-maurya/cursor-claude-personas)

## Projects
- PDFFusion (Python, FastAPI, AWS S3): Open-source microservice that merges PDFs and images from S3 presigned URLs, validated with qpdf. https://github.com/loannetwork/PDFFusion
- Ratn Tools Suite (TypeScript, Next.js): JSON validation and compression tools that run fully in the browser; data never leaves the device. https://tools.ratnesh-maurya.com/
- Ratn Tools: Developer utilities that run entirely in the browser — nothing you paste leaves the tab. https://tools.ratnesh-maurya.com/
- Personal Tracker: Habits, expenses, sleep and study in one PWA with its own analytics. https://tracker.ratnesh-maurya.com/
- JSONic: Fast JSON formatting, validation and diffing on real payloads. https://jsonic.ratnesh-maurya.com
- Rehabify: Patient records and treatment tracking for de-addiction centres. https://rehabify.ratnesh-maurya.com/
- mdconverter: Paste anything, get clean Markdown with a live preview. https://mdconverter.ratnesh-maurya.com
- npm-compare: Side-by-side npm package comparison with dependency analysis. https://npm-compare.ratnesh-maurya.com/

## Education
- B.Tech in CSE, Dr. APJ Abdul Kalam Technical University, Kanpur, India (2020 – 2024) — 8.0 CGPA
- Intermediate, Maharshi Patanjali Vidya Mandir, Allahabad, India (2017 – 2019) — 84.02%