AI Engineer with less than a year in Legal AI Systems & Generative AI
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Master's in Data Science from IIIT Lucknow and AI Engineer at MyLegacyBox, building production-grade Legal AI systems. Designed an end-to-end RAG pipeline for citation-grounded Indian legal Q&A, a Legal Validation Gate with a 5-component Priority Scorer, and deterministic PDF parsing for Indian court documents. Skilled in Generative AI, Agentic Frameworks, LLM Fine-tuning, and MLOps with experience delivering end-to-end AI pipelines in production.
Indian Institute of Information Technology, Lucknow
MSc · Data Science
August 1, 2024 – June 30, 2026
Lalit Narayan Mithila University, Darbhanga
BSc · Mathematics
August 1, 2018 – June 30, 2022
MyLegacyBox
AI Engineer Intern
February 1, 2026 – June 30, 2026
Lucknow, Uttar Pradesh, India
IIIT Lucknow
Teaching Assistant
August 1, 2024 – February 28, 2025
Patna, Bihar, India
MedQuery AI
June 1, 2026 – Present
AI-powered medical health companion using LLMs and RAG for intelligent, context-aware healthcare Q&A. Integrated Groq LLMs, LangChain, and Pinecone for context-driven medical info retrieval through RAG pipelines. Ingested and embedded medical books and research papers to enhance knowledge and reduce hallucinations. Deployed using AWS EC2 & ECR with automated CI/CD pipeline (GitHub Actions).
View ProjectEnd-to-End MLOps Lifecycle System
June 1, 2026 – Present
Production-grade MLOps platform for automated training, versioning, deployment, and monitoring of machine learning models. Built reproducible ML pipelines using DVC and parameterized workflows. Implemented MLflow tracking and model registry with Dagshub. Automated CI/CD pipelines using GitHub Actions for testing, Docker build, ECR push, and EKS deployment. Deployed Flask inference API on AWS EKS with monitoring via Prometheus and Grafana.
View ProjectPneumonia X-Ray Classification using Identity-Mapping ResFormer
June 1, 2026 – Present
Deep learning model for multi-class pneumonia detection using a custom ResFormer architecture. A ResFormer architecture integrating MCCRM, EMPT, IMTM, and SimAM modules for improved generalization. Achieved high accuracy on COVID-19 Radiography images using a PyTorch-based training pipeline.
View ProjectFinancial LLM – Fine-Tuning LLaMA-3-8B using QLoRA & Unsloth
June 1, 2026 – Present
Memory-efficient large language model fine-tuned for financial question answering using retrieval-augmented generation. Fine-tuned LLaMA-3-8B using QLORA and Unsloth for memory-efficient single-GPU training. Built RAG pipeline with FAISS for context-aware question answering. Optimized training using PEFT, LORA adapters, and 4-bit quantization. Evaluated model using Exact Match and Semantic Similarity.
View ProjectCultural Fit Analysis
The candidate's project portfolio showcases a strong interest and hands-on experience in cutting-edge AI/ML domains, particularly Generative AI and MLOps, which aligns well with an AI Engineer role. The diversity of projects, from medical Q&A to financial LLMs and legal RAG systems, indicates adaptability and a broad technical curiosity. Their academic background in Data Science further reinforces their commitment to the field. The candidate's proactive approach to personal projects demonstrates initiative and a drive for continuous learning, which are positive indicators for cultural fit in an innovative environment.
Soft Skills & Operational Fit
The candidate's project descriptions indicate strong problem-solving skills, particularly in tackling complex real-world challenges like legal document processing and hallucination reduction in LLMs. The detailed explanations of their contributions suggest a methodical approach to engineering and a focus on practical, production-grade solutions. Their role as a Teaching Assistant also implies good communication and mentoring abilities.