Help & Supportcareers@gravityer.com
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Amazon
Data Scientist
June 24, 2026 – Present
RiskOS-Marketplace-Intelligence
March 25, 2026 – Present
📊 Secure NL→SQL analytics layer for non-technical users. Ask questions about marketplace data in plain English to get instant structured results and Plotly charts. Features a multi-stage SQL safety gate, hybrid rule/LLM engine, and automated high-fidelity data seeding.
View ProjectRiskOS-LLM-Guard
March 25, 2026 – Present
Unsafe LLM outputs in a financial or risk context can lead to data leaks, regulatory violations, and reputational damage. Unlike basic keyword filters, RiskOS LLM Guard uses RAG-augmented policy evaluation and semantic classification to detect complex adversarial attacks, prompt injections, and PII exposure before they reach the user.
View ProjectRiskOS-Risk-Pipeline
March 24, 2026 – Present
ML-powered transaction triage with LightGBM scoring and 15-rule engine. Achieves ~70% workload reduction through intelligent risk filtering. FastAPI backend with batch processing, designed for high-throughput fraud detection systems. Part of RiskOS intelligence platform.
View Projectriskos-aml-intelligence
March 24, 2026 – Present
Multi-agent AI system for real-time fraud detection, credit risk assessment, KYC identity verification, and sanctions screening. Built with XGBoost, LightGBM, and IsolationForest for sub-100ms latency.
View Projectfraud-detector-open-webui
August 8, 2025 – August 8, 2025
Built using Open WebUI + Ollama + LLaMA 3
View Projectefficient-domain-tuning
August 3, 2025 – August 3, 2025
Research paper on efficient fine tuning of small sized open source models for domain specific tasks.
View ProjectSmolLM3-RAG-Project
July 25, 2025 – July 27, 2025
SmolLM3-RAG: A High-Performance, Low-Cost RAG System
View Projectopen-source_risk_framework
June 20, 2025 – August 24, 2025
open-source_risk_framework — repository
View ProjectMachine-Learning-Earthquake-Analysis-Prediction
November 4, 2023 – November 4, 2023
This project has the potential to make a significant contribution to earthquake prediction. By using machine learning, it may be possible to develop more accurate and reliable earthquake prediction models. This could help to save lives and reduce the damage caused by earthquakes.
View ProjectCultural Fit Analysis
The candidate's projects are heavily concentrated on 'RiskOS' and related financial/risk intelligence, indicating a strong interest in a specific domain. While this shows depth, the lack of diversity in project types outside this niche might suggest a narrower range of interests or experiences, potentially impacting broader cultural fit in a diverse team or product environment. The current role at Amazon as a Data Scientist aligns well with the target role.
Soft Skills & Operational Fit
Insufficient data to assess soft skills and operational fit. The candidate's project descriptions indicate a focus on practical problem-solving and system building.