AI Specialist Automating Workflows & Building AI Solutions
New to Contra
AI Specialist Automating Workflows & Building AI Solutions
Hybrid Semantic Search Engine
Keyword search misses results that mean the same thing in different words. Pure vector search misses exact matches.
I built a hybrid search engine that combines both. Text is embedded with the all-MiniLM-L6-v2 sentence model and indexed in FAISS, and each query blends vector similarity with fuzzy text matching (weighted 70/30), so results match on meaning and on exact terms.
Built as a FastAPI backend with a React frontend, packaged with Docker so it runs with one command.
What this shows: I understand how retrieval works under the hood, the same retrieval that powers RAG chatbots, and where it fails.
0
19
OpenTruth: Independent Verification Protocol
Claims made by AI systems and organisations are hard to check, and the evidence behind them can be quietly changed after the fact.
I built OpenTruth, an independent verification protocol that links each claim to its supporting evidence in a hash-protected evidence graph. Because every piece of evidence is hashed, any later tampering becomes detectable, and anyone can trace a claim back to exactly what supports it.
What this shows: I can design trust and verification systems end to end, from the data model to the integrity guarantees.
0
33
AI Coding Agent & Voice Model Evaluation
Ongoing paid work evaluating frontier AI models for an AI training platform.
For coding agents, I work through the same real-world bug in a codebase with two different agents, then score each on six quality dimensions plus a head-to-head comparison: correctness, reasoning, tool use, and where each one went wrong.
For voice models, I rate AI narration quality against detailed rubrics and review other evaluators' work for accuracy and consistency.
What this shows: I know how leading AI agents actually fail on real tasks, and I can evaluate them rigorously and consistently, which is exactly what teams need before shipping an AI feature.
0
26
Sentinel: MCP Security Guard Benchmark
Problem: MCP guard tools claim to block attacks on AI agents, but there was no consistent way to hold them accountable.
What I built: A benchmark with a sandboxed testing harness that runs guard tools against 6 classes of attacks in a controlled environment, so their protection can be measured and compared fairly.
Skills: AI security, MCP, adversarial testing, Python, sandboxing, benchmarking
Project 1 — E-Commerce ELT Pipeline
Title: E-Commerce ELT Pipeline — Airflow · dbt · BigQuery
Description: End-to-end ELT pipeline on 99.4K Brazilian e-commerce orders. Airflow orchestrates daily ingestion into BigQuery → dbt transforms across staging to mart layers. Surfaced R$16.4M customer LTV and R$1.25M peak monthly revenue for Looker Studio dashboards. 16 consecutive successful DAG runs under 6 minutes.
Link: https://github.com/Krupa03/ecommerce-elt-pipeline
0
59
Project 4 — RAG Document Chatbot
Title: RAG Document Chatbot — LangChain · ChromaDB · Streamlit
Description: Fully local RAG application: PDF ingestion → 500-token semantic chunking → 73-chunk ChromaDB vector store → LangChain retrieval chain with source citations and multi-turn memory. Streamlit UI, no external API dependency.
Link: https://github.com/Krupa03/rag-document-chatbot
0
36
Project 3 — Data Quality Checker
Title: Data Quality Checker — AWS S3 · Terraform · GitHub Actions
Description: A CLI tool automating data quality checks (nulls, duplicates, referential integrity, freshness, and schema drift) on a Kimball star-schema warehouse. AWS S3 provisioned as IaC with Terraform. Full CI/CD via GitHub Actions on every push.
Link: https://github.com/Krupa03/data-quality-checker