AI Engineer with 2+ years in LLM applications & cloud-native AI services.
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 Engineer with 1.5 years of experience building production-grade LLM applications, agentic workflows, and cloud-native AI services. Rapidly promoted from Intern to Data Engineer (L2) within 8 months at RR Donnelley and recognised with the Best Performance Award (R&R 2025). Expert in LLM orchestration, prompt engineering, Retrieval-Augmented Generation (RAG), and AWS Bedrock integration. Consistently converts unstructured inputs into client-ready outputs (PPT, Excel, Word) and ships scalable, enterprise-grade pipelines.
Loyola College
B.Sc. · Mathematics
N/A – June 30, 2022
Vellore Institute of Technology
M.Sc. · Data Science
N/A – June 30, 2025
RR Donnelley
Data Engineer
February 1, 2025 – Present
India
RR Donnelley
Data Analyst Intern
February 1, 2025 – October 1, 2025
India
SCOOP - Research Automation Platform (3-Version Evolution)
February 1, 2025 – June 1, 2026
End-to-end AI platform that automates analyst research workflows, producing structured insights and client-ready multi-format reports (PPT, Excel, Word) through LLM orchestration. Evolved iteratively from a static proof-of-concept to a fully configurable, cloud-native system. • Version 1 — Static Pipeline: Built the foundational platform with hardcoded prompts and a single fixed output format. Established the core LLM orchestration architecture and validated end-to-end data flow from raw inputs to a structured report, serving as the proof-of-concept for stakeholder buy-in. • Version 2 — Configurable & Multi-Format Output: Re-architected the platform for full developer-assisted configurability and rich output flexibility: • Prompt Configuration: Replaced hardcoded prompts with a developer-guided prompt-builder, allowing users to define their own query intent; the system provides structure, validation, and context enrichment. • Content Placeholders: Introduced a placeholder selection system for PowerPoint output — users pick which content populates each slide element (title, body, footer, etc.) without touching template files. • Multi-Format Output Engine: Users choose output content type per section — tables, bullet lists, charts, or shapes — and the system dynamically generates the appropriate element in PPT, Excel, or Word. • Modular Architecture: Designed reusable pipeline components, enabling rapid rollout of new output formats and report templates with minimal code changes. • Version 3 — Cloud-Native AWS Migration (In Progress): Migrating the full platform to a scalable, serverless cloud architecture: • Replacing local LLM inference with Amazon Bedrock (Anthropic Claude models) for managed, scalable LLM serving. • Moving document storage and report artefacts to AWS S3; decoupling pipeline stages using AWS Lambda for event-driven execution. • Designing cloud-native prompt configuration and retrieval services to support concurrent multi-user workflows at enterprise scale.
DocuLenz - Intelligent Lease Document QA
February 1, 2025 – October 1, 2025
• Developed an OCR and retrieval pipeline using MiniCPM for text extraction from scanned and digital PDFs with bounding-box precision. • Integrated an LLM-driven Q&A layer over chunk-based retrieval, enabling natural-language queries against complex lease documents. • Implemented page-level metadata storage for traceable, citation-backed responses.
Python 101 for Data Science
IBM CognitiveClass
June 1, 2026 – Present
Best Performance Award (R&R 2025)
RR Donnelley
January 1, 2025 – Present
Cultural Fit Analysis
The candidate's experience with diverse projects (research automation, document QA, various content generators) and technologies (multiple LLMs, cloud platforms, vector databases) indicates adaptability and a broad skill set, aligning well with dynamic AI engineering environments. Their involvement in cloud migration and designing modular microservices suggests a forward-thinking approach and a good fit for organizations embracing modern, scalable architectures. The recognition for high-impact AI solutions and rapid promotion points to a strong drive for excellence and contribution.
Soft Skills & Operational Fit
The candidate demonstrates strong problem-solving skills through iterative platform evolution and re-architecture. Their rapid promotion and performance award indicate a proactive, results-oriented work attitude and strong delivery capabilities. The ability to lead migrations and design scalable microservices suggests leadership potential and a strategic mindset. The focus on end-user configurability and multi-format outputs highlights a user-centric approach to development.