Backend / AI-Infrastructure Engineer · Pune, India

I build the control plane for AI agents.

What an agent is allowed to do, and whether you can trust what it concluded. Below is a running service graph. Break it, and watch an agent diagnose the incident you just caused — then watch it keep that answer after you take the evidence away.

239★ across 6 tools AWS SA Associate B.Tech, May 2026

A live service graph: ingress → api-gateway → checkout-api → postgres/redis, with traffic flowing between replicas. Inject a fault and an agent investigates it.

0 req/s 0.0% err healthy
inject a fault
evidence —
  • waiting for an incident

Not a video and not a mock-up — a service graph simulated in the page, with the fault types and evidence taken from KLRB's scenarios. Open to backend / AI-infrastructure / platform roles.

The system

Three of these are not separate projects. They are one control plane, built in the order I discovered I needed them — and they call each other. Every box below is a repository you can read.

a request from an AI agent

Atlas authorize Scoped, attenuable capability tokens bound to SPIFFE workload identity. Verified fully offline. Go · SPIRE · gRPC · MCP ★ 40 attenuating — narrower on every hop, never wider AISRE act Detects a live failure, investigates with a three-tool agent, proposes a root cause. Python · Nemotron · Flask new no remediation without human approval structured-JSON root cause KLRB evaluate Did the model read the cluster evidence, or guess confidently without it? Python · Kubernetes · chaos ★ 96

a conclusion you can check

Adjacent — same question, one layer down

tf.why attribute

Terraform tells you what drifted. This tells you who changed it, when, and from where — by correlating the plan against CloudTrail.

Python · Terraform · AWS CloudTrail · IAM ★ 33

Atlas asks whether a caller may act. tf.why asks who already did. It does not wire into the pipeline above — it is a standalone CLI, and I would rather say so than draw an arrow that isn't there.

Earlier work

There are ~60 repositories on my GitHub. These six are the ones worth your time; the rest are coursework, forks and experiments, and I would rather point you at four good things than forty.

Background

Education

MIT ADT University, Pune
B.Tech, Electronics & Computer Engineering
Aug 2022 – May 2026 · CGPA 7.71 / 10

Certifications

  • AWS Certified Solutions Architect – Associate
  • AWS Certified AI Practitioner
  • AWS Certified Cloud Practitioner
  • GitHub Copilot Certified
  • Redis Certified Developer (Python)

Skills

Languages
Go, Python, SQL, Bash
AI / agent infrastructure
Model Context Protocol (MCP), agent authorization, LLM evaluation harnesses, tool & function calling, structured outputs, RAG
Backend
gRPC, REST, JSON-RPC, FastAPI, Flask, PostgreSQL, Go concurrency
Cloud & infra
AWS (EC2, IAM, S3, CloudWatch), Docker, Kubernetes, GitHub Actions, Nginx, Linux
Security
SPIFFE/SPIRE workload identity, capability-based authorization, mTLS, JWT, least-privilege design

Hiring for backend, platform, or agent infrastructure?

I am looking for a first role where the hard part is correctness under adversarial conditions — authorization, evaluation, incident response. Happy to walk you through the 12 deployment defects the Atlas audit found, or why KLRB's ablation is the only honest way I know to score an AI incident responder.