DEV Community

Vishva R profile picture

Vishva R

AI Engineer (1.5 yrs) building agentic systems with CrewAI/LangChain, RAG apps, and low‑latency LLM inference (Llama.cpp/vLLM/Ollama). Streamlit frontends. Docker → AWS ECR/ECS. RunPod LoRA/QLoRA.

Location Chennain, Tamilnadu, India Joined Joined on  Personal website https://github.com/vishvaRam

Education

B.Tech Informtion Technology

Work

NCS Soft sloutions, Chennai

CrewAI Crews & Flows: The Complete Guide to AI Workflow Orchestration

CrewAI Crews & Flows: The Complete Guide to AI Workflow Orchestration

Comments
6 min read
RAG with LLMs: The Complete Guide to Retrieval-Augmented Generation

RAG with LLMs: The Complete Guide to Retrieval-Augmented Generation

2
Comments
5 min read
RunPod Cloud Computing: The Ultimate Guide for AI/ML Developers

RunPod Cloud Computing: The Ultimate Guide for AI/ML Developers

Comments
5 min read
ChatGPT 5: The Complete Guide to OpenAI's Next-Gen AI

ChatGPT 5: The Complete Guide to OpenAI's Next-Gen AI

Comments
6 min read
Gemma 3 270M: The Ultimate Guide to Compact AI Power

Gemma 3 270M: The Ultimate Guide to Compact AI Power

Comments
6 min read
Unlock LLM Precision: Master Structured Output with Pydantic and Instructor

Unlock LLM Precision: Master Structured Output with Pydantic and Instructor

Comments
6 min read
The Precision Revolution - Unlocking Structured Output from LLMs

The Precision Revolution - Unlocking Structured Output from LLMs

Comments
4 min read
OpenAI's GPT-OSS: The Dawn of a New Open-Weight AI Era

OpenAI's GPT-OSS: The Dawn of a New Open-Weight AI Era

Comments
6 min read
loading...