Swastik Mukherjee - AI Engineer & Full Stack Developer
AI Engineer & Full‑Stack Developer
Shipping AI‑powered web apps, multi‑agent systems, and ML pipelines. I build end-to-end—from training models to deploying production backends.
I’m Swastik Mukherjee, a Full Stack and AI developer who builds intelligent, real-world applications at the intersection of software engineering and machine learning. I specialize in creating scalable products that move from idea to deployment.
Projects
Year
Learning
Projects
Each built from scratch, shipped to real users, and maintained in production.
HelixAI
Local-first multi-agent orchestration system
Desktop AI orchestrator that runs complex workflows without cloud dependency.
- Decomposes user requests into DAG task workflows, routes to specialized workers via Redis Streams
- Handles LLM inference (Ollama), tool execution, RAG lookups, and streaming outputs locally
- FastAPI orchestrator + PostgreSQL state + Qdrant vector search, all running on your machine
Real-Time Fraud Detection
Streaming fraud scoring pipeline with low-latency inference
Scores transactions in real-time using XGBoost converted to ONNX.
- XGBoost model converted to ONNX for fast CPU inference in production
- Spring Boot backend serves predictions with feature preprocessing pipeline
- Next.js dashboard for monitoring fraud patterns and model performance
FaceCheck.AI
CNN classifier for real vs. AI-generated faces
Detects synthetic faces using a custom CNN trained on a large dataset.
- Custom CNN architecture trained on real vs. AI-generated face dataset
- FastAPI backend serves TensorFlow/Keras inference with confidence breakdowns
- Clear API boundaries between frontend and ML backend, containerized with Docker
MindMend
AI-backed journaling and mental wellness platform
Conversational journaling app with structured AI responses and voice interactions.
- Gemini-powered conversations with ElevenLabs voice synthesis for accessibility
- Progress tracking, mood journaling, and reflective dialogue features
- Firebase Auth + MongoDB Atlas backend, deployed on Vercel
I'm best at wiring up AI models to real products—from data to model to UI.
Languages
Core programming languages I use daily in production.
Languages
Core programming languages I use daily in production.
Full-Stack
Frameworks and tools I reach for when building web apps.
AI / ML
Core frameworks and libraries I use for building, training, and deploying ML systems and workflows.
Tools & Infrastructure
Dev tooling and infrastructure I rely on for building routes to production.
Contact
Looking for an
AI or full‑stack intern?
2nd-year B.Tech student. I build real systems, ship working code, and own features end-to-end. Available for internships.