Backend & AI Engineer building product-grade Node.js/Express systems, APIs, integrations, and reliable agent workflows.
B.Tech CSE - Data Science & Analytics @ IIIT Nagpur - 2027
Backend-heavy MERN - Agent Systems - APIs - Reliability
- Product backends - Node.js/Express APIs, service boundaries, authentication, sessions, billing, webhooks, integrations, and data access.
- Full-stack AI products - React workspaces backed by MongoDB/PostgreSQL, Redis, object storage, and deployable API services.
- Reliable agent systems - LangGraph orchestration, persistence, tool use, retrieval, human review, evaluation, and failure handling.
I care as much about what happens when the model is wrong as when it is right.
| Project | What it demonstrates | Tech |
|---|---|---|
| CortexAI - AI Developer Platform & Integration Workspace | Full-stack AI workspace with a React client, Express API gateway, auth/chat/agent/billing services, MongoDB and Redis persistence, LangGraph routing, RAG, multimodal workflows, and generated artifacts. | Node.js, Express, React, MongoDB, Redis, LangGraph, Qdrant |
| North Star - Governed Expense Operations Platform | Governed expense operations and workflow automation platform with deterministic policy enforcement, 13 durable n8n workflows, advisory AI, human approvals, SHA-256 provenance, notification integrations, and real-time SSE updates. | Python, FastAPI, React, TypeScript, PostgreSQL, n8n, MCP |
| SifraAI - Deployed Voice AI Product | Deployed MERN-style voice assistant product with Firebase auth, cookie/JWT sessions, MongoDB, Razorpay billing, Gemini, an embeddable JavaScript widget, and third-party website integration. | React, Node.js, Express, MongoDB, Firebase, Razorpay, Gemini |
| AI Platform Reliability Copilot | FastAPI reliability system with a public API, Streamlit interface, incident clustering, risk scoring, runbook retrieval, Redis state, OpenTelemetry, Prometheus/Grafana, Slack alerting, and a six-stage CI pipeline. | Python, FastAPI, Redis, OpenTelemetry, Prometheus, Grafana, Helm |
| RevenueGuard AI - Explainable Payment Recovery | Event-driven payment-recovery platform with webhook ingestion, ML triage, gateway-health intelligence, Redis-backed workers, PostgreSQL, LangGraph decisions, deterministic policies, and human approval for high-value actions. | Python, FastAPI, LangGraph, PostgreSQL, Redis, Razorpay, React |
| Retail Lakehouse Engineering | Replay-safe PostgreSQL CDC pipeline orchestrated by Airflow, landed in Delta Lake with Spark, and published through dbt silver/gold models; locally verified with 42,796 events and a 38/38 dbt build. | PostgreSQL, Airflow, PySpark, Delta Lake, dbt, Docker |
| Project | What it demonstrates |
|---|---|
| TripBandhu - Stateful Agentic Travel Research | Stateful LangGraph travel research with five specialists, typed evidence, PostgreSQL checkpoints, provider reliability controls, and interrupt/resume human review. |
| Internal RFP Analyst | Cyclic agentic RAG for evidence-grounded RFP analysis with adaptive retrieval, evidence grading, citation verification, bounded repair, and 145 passing tests. |
| Financial Document Intelligence | Local-first SEC filing RAG with section-aware parsing, hybrid dense and BM25 retrieval, grounded citations, source URLs, no-answer handling, and evaluation tooling. |
AI is part of my normal build loop, but I do not treat "the agent says it works" as completion. I use coding agents for repo exploration, implementation, tests, repetitive changes, and debugging, then verify behavior with tests, CI, traces, logs, and the running system. The architectural and product decisions stay mine.
| Area | Tools and Technologies |
|---|---|
| Backend & APIs | Node.js, Express, FastAPI, REST APIs, service boundaries, authentication, sessions, webhooks, billing |
| Full-stack | React, TypeScript, JavaScript, MongoDB, PostgreSQL, Redis, SQL, SQLAlchemy |
| Agents & GenAI | LangGraph, LangChain, MCP, RAG, tool calling, structured outputs, HITL, guardrails, provenance, agent evaluation |
| Reliability & Infrastructure | pytest, GitHub Actions, Docker, LangSmith, observability, SSE, n8n, failure handling |
| Integrations | AWS S3, Qdrant, Tavily, Metabase, Resend, Slack, Firebase, Razorpay |
| Data Engineering | PostgreSQL CDC, Airflow, PySpark, Delta Lake, dbt, replay-safe ingestion |
| Project | What it demonstrates | Tech |
|---|---|---|
| RideIQ - NYC Demand Forecasting & Fleet Intelligence | End-to-end mobility analytics on 9.55M NYC taxi trips: leakage-safe zone-hour forecasting, constrained fleet-allocation simulation, route clustering, dashboard delivery, and FastAPI service. | Python, Pandas, Scikit-learn, Streamlit, FastAPI, Geospatial Analytics |
| Retail Analytics & Data Pipeline System | Cloud-ready retail data platform from JSON/SharePoint sources through Azure Data Factory and PySpark into an Azure SQL star schema and Power BI dashboards. | Python, SQL, PySpark, Azure Data Factory, Azure SQL, Power BI, DAX |
| Vendor Performance Analysis | Retail analytics workflow over purchasing, sales, pricing, and freight data that surfaces vendor concentration, unit-cost scaling, profitability differences, slow-moving inventory, and assortment decisions. | Python, pandas, SQLAlchemy, SQLite, Power BI, SciPy |
| ReceiptKIE-VLM - Vision-Language Receipt Understanding | LoRA fine-tuning and evaluation pipeline for SmolVLM receipt extraction, reaching 99.2% valid JSON on 246 unseen SROIE test receipts. | Python, PyTorch, Transformers, PEFT/LoRA, SmolVLM, SROIE |
IIIT Nagpur. B.Tech CSE - Data Science & Analytics. Graduating 2027. Currently focused on backend-heavy full-stack engineering, reliable AI systems, and agent infrastructure. Available immediately for a 6-month Backend / AI / FDE internship.
I am open to Backend / AI / FDE internships and collaborations involving APIs, integrations, reliable systems, and agent workflows.
- Email: tg304429@gmail.com
- Portfolio: tushar-portfolio-taupe.vercel.app
- LinkedIn: linkedin.com/in/tushar-ghosh-a3355124a
- GitHub: github.com/tusharg007