Nikhil R. Nigam
Machine Learning Engineer
I build the infrastructure that makes AI reliable. From Sub-second Vector Search to Privacy-First RAG systems, I bridge the gap between research prototypes and production durability.
SYSTEM KERNEL [ONLINE]
Core
Python PyTorch Lightning LangChain TensorFlow
Infra
AWS (EC2/S3/EFS) Docker Milvus Flask Linux
Ops
MLflow W&B Git SQL
Selected Deployments
VIEW FULL ARCHIVE →2025
Meet-Me: The Digital Twin
An agentic RAG-based personal interface bridging the gap between static resumes and technical deep-dives.
<400ms TTFT (Time To First Token)
2024
Intelligent Model Recommendation
Sub-second recommendation engine analyzing high-dimensional meta-features via Milvus.
<1s latency
2024
Privacy-First OCR Pipeline
Hybrid compliance workflow using local Ollama models and EasyOCR.
100% Local Inference
2023
Generative MRI Restoration
Adapting Stable Diffusion to replace slow, iterative MRI correction with real-time generative inference.
68% Error Reduction
2022
Deep Learning for Wireless CSI Compression
Novel 3D Convolutional Autoencoder handling variable input dimensions for massive MIMO CSI feedback.
40% Bandwidth Reduction