SOUMYADEEP JANA
AI/ML Engineer | RAG & LLM Systems | Backend & Distributed Systems
object SoumyadeepJana {
val role = "AI/ML Engineer"
val focus = listOf(
"RAG",
"Long-Term AI Memory",
"Hybrid Retrieval",
"LLM Systems"
)
val backend = listOf(
"Python",
"Java",
"Spring Boot",
"Ktor"
)
val data = listOf(
"Kafka",
"PostgreSQL",
"S3",
"DuckDB"
)
val currentlyBuilding =
"Intelligent AI & scalable backend systems"
val philosophy =
"Build • Learn • Scale"
}
💼 Experience AI/ML Engineering Intern — Nexora AI Labs ⚡ Reduced API response time by 40% 🚀 Increased API throughput by 3× 📊 Processing 2M+ campaign events/month ⚡ Supporting 10,000+ reward events/minute 🔗 Processed 1M+ clicks 📱 Applications with 150K+ Google Play installs
🧠 Memora AI Intelligent RAG & Long-Term AI Memory Platform Hybrid retrieval using Qdrant + BM25 Entity-based retrieval Recency-aware memory selection Semantic, episodic & profile-based memory Hybrid ranking Token-budgeted context assembly Asynchronous retrieval pipeline SSE-based LLM streaming
🌍 GeoConnect AI Intelligent Geospatial Social & Professional Networking Platform Spring Boot microservices Flutter PostgreSQL + PostGIS API Gateway Real-time geospatial discovery QR-based social sharing
👋 Header ↓ 🧑💻 About Me ↓ 🧠 AI / ML ↓ ⚙️ Backend & Distributed Systems ↓ 📊 Data Engineering ↓ ☁️ Cloud & DevOps ↓ 📱 Application Development ↓ 🚀 Featured Projects ↓ 💼 Experience ↓ 📈 GitHub Stats ↓ 🤝 Connect With Me