Help & Supportcareers@gravityer.com
AI Engineer with less than a year in Data Analysis & Machine Learning
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI/ML enthusiast and B.Tech. student specializing in Data Science with a solid foundation in machine learning, data analysis, and multi-agent systems. Proven ability to design and implement AI-powered solutions for complex data challenges, enhance user experience through predictive analytics, and streamline data processing pipelines. Eager to apply technical skills and innovative approaches to develop cutting-edge AI applications and drive impactful insights.
ABES Engineering College
B.Tech · Computer Science Engineering (Data Science)
October 1, 2023 – June 1, 2027
KDB Public School
Class XII (Senior Secondary)
June 1, 2022 – May 31, 2023
Aurameter
Data Analyst Intern
October 1, 2025 – November 1, 2025
India
IBM Virtual Internship
AI/ML Intern
July 1, 2025 – August 1, 2025
India
EchoHeal- AI-Native Self-Healing CRM
June 1, 2026 – Present
Built EchoHeal, an AI-powered CRM platform using FastAPI and Streamlit, featuring customer segmentation, campaign orchestration, AI campaign generation, and real-time communication monitoring. Designed an event-driven webhook architecture to process delivery events and integrated a Groq-powered AI Recovery Agent that automatically rewrites failed messages and reroutes them through fallback communication channels. Deployed a production-ready multi-service architecture on Render and Streamlit Cloud, managing API integrations, cloud configuration, environment variables, and end-to-end service orchestration across frontend and backend components.
Veritas- Multi Agent AI Research System
April 1, 2026 – May 1, 2026
Architected and implemented Reader, Writer and Critique agents for a multi-agent AI research framework, streamlining the extraction, validation and refinement of information from web sources. Engineered a content-processing pipeline that transforms unstructured webpage data into clean, structured text, improving the quality and reliability of downstream report generation. Developed an automated quality-assurance layer that identifies information gaps, weak report structure, and missing insights, enhancing the coherence and factual grounding of final research reports.
Customer Churn Prediction
October 1, 2025 – December 1, 2025
Identified that month-to-month and short-tenure customers are 3 times more likely to churn, signaling a critical need for targeted early-retention loyalty programs. Pinpointed lack of "Tech Support" and "Online Security" as top churn drivers, suggesting that service bundling could improve retention rates by up to 20%. Discovered a high correlation between Electronic Check payments and attrition, highlighting the strategic need to transition users toward automated billing systems.
Cultural Fit Analysis
The candidate's projects demonstrate a strong interest and practical experience in AI/ML, which aligns well with an AI Engineer role. The diversity of projects, from predictive analytics to multi-agent systems and AI-native CRMs, shows a broad technical curiosity and willingness to explore different facets of AI. The listed education and internships, while still ongoing/recent, indicate a proactive approach to gaining relevant experience. However, the candidate is still early in their career, which might impact their fit for a senior-level role requiring extensive industry experience and leadership.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an ability to work on complex problems and contribute to end-to-end solutions. The focus on identifying actionable insights (Customer Churn Prediction) and developing automated quality assurance (Veritas) suggests a detail-oriented and problem-solving approach. The deployment of multi-service architectures (EchoHeal) implies an understanding of operational aspects, though direct experience in a senior operational role is not evident.