DEV Community

Srijan Verma profile picture

Srijan Verma

Building production-grade AI systems, LLM orchestration layers, and low-latency backend pipelines that actually scale.

Joined on  srijanatwork1@gmail.com
Stop Using Regex: Building Zero-Crash LLM JSON Pipelines in Production
srijan_bhai profile

Stop Using Regex: Building Zero-Crash LLM JSON Pipelines in Production

#ai #backend #softwareengineering #systemdesign
2
3 min read

Want to connect with Srijan Verma?

Create an account to connect with Srijan Verma. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
Surviving the 429 Storm: Building Resilient LLM Fallbacks in Production
srijan_bhai profile

Surviving the 429 Storm: Building Resilient LLM Fallbacks in Production

#ai #backend #softwareengineering #systemdesign
1
2 min read
Taming Context Bloat: How to Scale AI Agent Memory Without Breaking the Token Bank
srijan_bhai profile

Taming Context Bloat: How to Scale AI Agent Memory Without Breaking the Token Bank

#ai #backend #softwareengineering #systemdesign
1
1
2 min read
Stop Passing Full Chat Transcripts: Build a Two-Tier AI Memory System
srijan_bhai profile

Stop Passing Full Chat Transcripts: Build a Two-Tier AI Memory System

#ai #backend #softwareengineering #systemdesign
2 min read
Bulletproofing AI Agents: How to Prevent $2,000 Infinite API Loops
srijan_bhai profile

Bulletproofing AI Agents: How to Prevent $2,000 Infinite API Loops

#ai #backend #softwareengineering #systemdesign
1
2 min read
Stop Choosing Between RAG, Fine-Tuning, and Agents: Build the Hybrid Trio Instead
srijan_bhai profile

Stop Choosing Between RAG, Fine-Tuning, and Agents: Build the Hybrid Trio Instead

#ai #backend #softwareengineering #systemdesign
2
4
3 min read
Stop Leaking Data to Cloud APIs: Self-Hosting DeepSeek Locally with Ollama
srijan_bhai profile

Stop Leaking Data to Cloud APIs: Self-Hosting DeepSeek Locally with Ollama

#ai #backend #softwareengineering #systemdesign
2
1
2 min read
Deterministic Guardrails: Stop LLM Tool Calling Failures at Runtime
srijan_bhai profile

Deterministic Guardrails: Stop LLM Tool Calling Failures at Runtime

#ai #backend #softwareengineering #systemdesign
1
2
3 min read
Stop Using Naive Hugging Face Pipelines: Scale LLM Serving with vLLM
srijan_bhai profile

Stop Using Naive Hugging Face Pipelines: Scale LLM Serving with vLLM

#ai #backend #softwareengineering #systemdesign
2 min read
Stop Wasting Tokens: Building a Sub-50ms Semantic Cache with Redis
srijan_bhai profile

Stop Wasting Tokens: Building a Sub-50ms Semantic Cache with Redis

#ai #backend #softwareengineering #systemdesign
1
3 min read
Building Event-Driven AI Agents: Replacing Polling Loops with Redis Streams and Idempotent Workers
srijan_bhai profile

Building Event-Driven AI Agents: Replacing Polling Loops with Redis Streams and Idempotent Workers

#ai #backend #softwareengineering #systemdesign
1
2
4 min read
loading...