My technical foundation spans the full machine learning engineering stack: designing and fine-tuning deep learning models in PyTorch,
building production generative AI and RAG pipelines with LangChain and vector databases, and deploying scalable MLOps infrastructure
on Kubernetes and AWS. I work across model development, backend systems, and cloud tooling — from data ingestion and experiment
tracking through to serving and monitoring in production.
AI / ML
LLMs
RAG
Whisper ASR
Computer Vision
Transformers
LoRA / QLoRA
Prompt Engineering
Semantic Search
Vector Indexing
Feature Engineering
Fine-Tuning
Model Evaluation
Multimodal AI
Recommendation Systems
NLP
Deep Learning
Backend / Systems
Python
R
SQL
NoSQL
MongoDB
Cassandra
REST APIs
gRPC
ETL Pipelines
Kafka
Docker
Kubernetes
Bash
Web Scraping
Data Wrangling
Model Serving
Inference Optimization
Tools / Cloud
AWS
Azure
GCP Vertex AI
MLflow
Weights & Biases
GitHub Actions
FAISS
Pinecone
Weaviate
Hugging Face
LangChain
PyTorch
TensorFlow
scikit-learn
XGBoost
A/B Testing
Model Monitoring
Experiment Tracking