|
I build production AI systems that reason, plan, and execute autonomously — from multi-agent orchestration to enterprise RAG pipelines serving millions of requests. 🔭 Currently Building:
|
|
Production multi-agent orchestration with planner, coder & reviewer agents
|
Knowledge Graph + RAG with Neo4j for intelligent document QA
|
|
Enterprise-grade RAG with hybrid search, guardrails & observability
|
Natural Language → SQL with schema understanding
|
|
Build Small Language Models from zero — tokenizers to RLHF
|
Production fine-tuning with LoRA, QLoRA — deploy in hours
|
📋 Full Tech Breakdown
LLM Providers OpenAI • Anthropic • Google Gemini • Llama • Mistral
Agent Frameworks LangGraph • Google ADK • CrewAI • AutoGen • MCP Tools • A2A
RAG Stack LangChain • LlamaIndex • Neo4j • Pinecone • Weaviate • OpenSearch
Observability Langfuse • MLflow • Weights & Biases • OpenTelemetry
Inference vLLM • TensorRT-LLM • Triton • ONNX Runtime
Fine-tuning PEFT • LoRA • QLoRA • Unsloth • Axolotl • DeepSpeed
Frontend React • Vite • Next.js • TypeScript • TailwindCSS
Backend FastAPI • Python • Node.js • GraphQL
Cloud AWS (Bedrock, SageMaker) • GCP (Vertex AI) • Azure
Infrastructure Docker • Kubernetes • Terraform • GitHub Actions
📂 More Projects
| Project | Description |
|---|---|
| Spark_cum_GPU_sentiment_analyzer | Distributed sentiment analysis with PySpark & GPU |
| Vector-Database-Benchmark | Performance benchmarks for vector databases |
| Lead-Scoring | ML-based lead scoring system |
| Deep-Learning-Projects | Collection of DL implementations |
