Skip to content

Navigation Menu

Sign in
Sign up
@JustRK-07
JustRK-07
Follow

Rushabh Kalme JustRK-07

Highlights

  • Pro

Block or report JustRK-07

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
JustRK-07 /README.md

Rushabh Kalme — Personal Portfolio

Backend & distributed-systems engineer · Pune, India
Cummins Inc. Merit Scholar '25

Portfolio Email LinkedIn Codeforces


Currently

  • IntelliCredit — scaling the 7-agent LangGraph credit pipeline through a third bank's underwriting workflow.
  • ISGEC ×ばつ ADV — wrapping the semester-long industry engagement with ISGEC Heavy Engineering Limited; CAD validation POCs across sugar, boiler, and crane divisions.
  • Open to full-time roles starting 2026 (backend / distributed systems / applied AI).

Selected work

Project What it is
🏗️ ADV — CAD Drawing Validation 78 pytests / 91% coverage · 8-rule geometric engine + async LLM pass · Phase 1 in ~1.8s on 17.8K-entity real General Arrangement drawings · industry engagement with ISGEC Heavy Engineering
🏦 IntelliCredit 7-agent LangGraph pipeline · 3–6 weeks → ~4 minutes · AA + GSTR-2A/3B reconciliation · counterfactual reasoning · RBI-aligned memo
🔬 OS-Devin Eval Harness 4-agent LangGraph system · 18 tasks ×ばつ 4 configs ×ばつ 3 LLM backends · tree-sitter-validated evaluation harness
📈 Foretell Vista PyTorch STGNN · FedAvg across retail silos · 14.2% → 11.1% MAPE · SHAP + DoWhy causal inference
🚆 Rail Yard Slot & Conflict Manager Java 21 / Spring Boot 4.0 / Angular 21 / PostgreSQL 17 · partial GiST-exclusion constraint for conflict-free reservations · 3-job GitHub Actions CI
🛡️ AfterMath — SRE Agent DARC loop with Hindsight memory · refuses fixes that have backfired · decays weak fixes · Bank of India CyberShield 2026 entry
📜 SAR-AI — AML Compliance 5-agent SAR narrative generator · sentence-level audit provenance · Constitutional AI · React Flow transaction graph

Stack

Python · TypeScript · Java · C++ · SQL · LangGraph · LangChain · FastAPI · PostgreSQL · Redis · WebRTC · LiveKit · React · Next.js · Astro · Tailwind · PyTorch · TFLite · GCP · Docker · Kubernetes

Reach out

The cream/orange editorial portfolio lives in JustRK-07/portfolio — Astro 5 + MDX + Tailwind 3.4. Card covers generated via the mmx-cli image skill.

Popular repositories Loading

  1. InPactAI InPactAI Public

    Forked from AOSSIE-Org/InPactAI

    Inpact is an open-source AI-powered platform designed to connect content creators, brands, and agencies through data-driven insights. By leveraging Generative AI (GenAI), audience analytics, and en...

    TypeScript

  2. website website Public

    Forked from asyncapi/website

    AsyncAPI specification website

    TypeScript

  3. electron electron Public

    Forked from electron/electron

    :electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS

    C++

  4. Multi-Stakeholder-Demand-Forecasting-and-Inventory-Optimization-with-Causal-Inference-GNNs Multi-Stakeholder-Demand-Forecasting-and-Inventory-Optimization-with-Causal-Inference-GNNs Public

    Foretell Vista — PyTorch STGNN with FedAvg across retail silos, causal attribution via SHAP + DoWhy, RL replenishment via Ray RLlib. 14.2% -> 11.1% MAPE across 4,200 SKUs.

    TypeScript

  5. SAR-AI-Multi-Agent-Compliance-Automation-with-Sentence-Level-Audit-Provenance SAR-AI-Multi-Agent-Compliance-Automation-with-Sentence-Level-Audit-Provenance Public

    SAR-AI — 5-agent Suspicious Activity Report narrative generator with sentence-level audit provenance; Constitutional AI prevents speculation beyond retrieved evidence.

    Python

  6. IntelliCredit-Multi-Agent-Credit-Appraisal-via-Account-Aggregator-GSTR-Reconciliation-Counterfactual IntelliCredit-Multi-Agent-Credit-Appraisal-via-Account-Aggregator-GSTR-Reconciliation-Counterfactual Public

    7-agent LangGraph pipeline: ingests via Account Aggregator, reconciles GSTR-2A vs GSTR-3B for ITC fraud, computes buyer-concentration risk, and produces an explainable Credit Appraisal Memo with co...

    TypeScript

AltStyle によって変換されたページ (->オリジナル) /