Senior ML Engineer - Production ML & Real-Time Systems

VIMAL KUMAR

Machine Learning Engineer • Production ML • Real-Time Systems • GenAI

+91-790******* • *********@*****.*** • LinkedIn • GitHub PROFESSIONAL SUMMARY

Machine Learning Engineer with hands-on experience delivering production ML systems and GenAI applications across the full development lifecycle. Built real-time fraud detection at sub-200ms latency, a secure enterprise RAG pipeline achieving MRR=0.833 with zero unauthorized data leaks, and a live AI recruiter tool in production. Strong in Python, FastAPI, Docker, and cloud infrastructure, with a consistent track record of measurable impact: 92% model accuracy, 15% performance uplift, and 60K MAE. WORK EXPERIENCE

Machine Learning Intern Jun 2025 – Jul 2025

Unified Mentor Private Limited • Remote

Developed and evaluated ML models on 5,000+ clinical records for liver cirrhosis staging, achieving 92% diagnostic accuracy and supporting data-driven clinical insights.

Built and validated a vehicle price prediction model achieving 60K MAE using XGBoost and Optuna hyperparameter tuning on real-world automotive datasets.

Improved model performance by 15% through systematic feature engineering, stratified cross-validation, and structured experimentation workflows.

Established ML best practices across the team including Git-based versioning, reproducible training pipelines, and deployment-ready model packaging.

PROJECTS

Real-Time Fraud Detection ML Platform GitHub

Apache Kafka · FastAPI · MLflow · Docker · Prometheus · Grafana · Isolation Forest

Architected a Kafka-based streaming ML system delivering fraud predictions at sub-200ms end-to-end latency, production-grade for high-frequency financial transaction data.

Built a complete MLOps pipeline with MLflow experiment tracking, Dockerized microservices, automated model versioning, and one-command reproducible deployment.

Implemented Prometheus + Grafana observability stack to monitor API latency, throughput, and real-time model drift detection across streaming inference.

Trained and tuned an Isolation Forest anomaly detection model achieving high-precision fraud identification with low false-positive rates on imbalanced streaming data. Enterprise RAG Intelligence System Live Demo

Python · NumPy · FastAPI · Streamlit · Docker · Claude API · RBAC · MMR Reranking

Engineered a production RAG pipeline from scratch without LangChain, implementing hybrid TF-IDF + cosine retrieval with MMR diversity reranking across 10 multi-format enterprise documents (PDF, CSV, JSON).

Achieved MRR=0.833, NDCG@5=0.799, Precision@5=0.645, and P95 latency=2.7ms measured via a purpose-built evaluation framework with hallucination risk scoring.

Designed two-layer RBAC (clearance hierarchy + per-document role whitelist) that blocked 21 unauthorized data accesses with zero leaks, validated by 17 passing unit and integration tests.

Delivered a complete production stack: FastAPI REST API with Swagger docs, interactive Streamlit UI, Docker Compose deployment, and per-query audit logging with confidence tracking. AI Talent Intelligence Platform Live Demo

Scikit-learn · XGBoost · LangChain · FAISS · FastAPI · MLflow · Streamlit · HuggingFace

Built and deployed a live AI recruiter tool that automatically ranks, scores, and matches resumes to job descriptions using Scikit-learn and XGBoost classification models.

Implemented RAG-based resume Q&A and semantic candidate search using LangChain, HuggingFace embeddings, and FAISS vector store for natural-language querying over candidate pools.

Integrated MLflow experiment tracking and a Streamlit recruiter dashboard for candidate comparison, resume scoring insights, and model performance visibility. TECHNICAL SKILLS

Languages Python, SQL (window functions, CTEs, aggregations, subqueries) ML / Data Scikit-learn, XGBoost, Isolation Forest, TensorFlow, Pandas, NumPy GenAI & NLP LLMs, RAG, RBAC, MMR Reranking, Claude API, OpenAI API, HuggingFace, FAISS, Sentence Transformers

MLOps & APIs MLflow, EvidentlyAI, SHAP, FastAPI, REST APIs, Docker, CI/CD Pipelines Cloud & Infra AWS (S3, EC2), Apache Kafka, Prometheus, Grafana, Git, Linux (Ubuntu) EDUCATION

B.Tech, Computer Science & Engineering Nov 2020 – Jul 2024 Rajkiya Engineering College

CERTIFICATIONS

Machine Learning – From Basics to Advanced (Udemy)

Data Science Master Class – End-to-End ML using Python (Udemy)

Contact this candidate