Hi, I’m Krishna Singh, a specialized AI/ML Engineer with a focus on building production-grade Generative AI applications and scalable distributed systems. Whether it's deploying high-performance LLMs or automating complex workflows with AI agents, I bridge the gap between AI research and real-world software. I have extensive experience in LLMOps, where I optimize models using quantization (vLLM, ONNX) to reduce latency and infrastructure costs. My expertise extends to building advanced RAG (Retrieval-Augmented Generation) pipelines and Multi-Agent Orchestration (using CrewAI/LangGraph) to automate tasks that traditional software can't handle.
What I Bring to Your Project:
Generative AI: Custom RAG pipelines, fine-tuning (LoRA/QLoRA), and Tool-Calling Agents.
LLMOps: Deploying and scaling models on AWS using Docker and vLLM for maximum efficiency.
Automation & Trading Bots: Experience in building high-frequency trading bots (e.g., Polymarket) and real-time data pipelnes.
Data Extraction: Advanced PDF parsing for financial and technical documents (Project: Offshore & Roznahub).
Scalable Backend: Expert-level Python with FastAPI, Redis, and Celery for high-throughput workloads.
Why Hire Me?
Performance Driven: I don't just "make it work"—I optimize. I’ve previously improved inference latency by 32% and retrieval accuracy by 18% in production environments.
Production-Ready: My code is modular, well-documented, and ready for deployment using modern CI/CD practices.
End-to-End Delivery: From AI research to frontend integration via WebSockets/APIs,
I handle the full lifecycle of the project. Let's turn your AI vision into a scalable reality. Message me today to discuss your project!