Headline

SDE 1 - Applied AI @ Krutrim | AI Engineer | Python · LLMs · GenAI · Backend Systems | Contributing to India’s AI Journey

About

Software Developer with expertise in building scalable backend systems, LLM-powered tools, and data-intensive pipelines. Proficient in Python frameworks (Django, Flask, FastAPI), with frontend experience in React. Skilled in PySpark, MongoDB, and advanced PostgreSQL (JSON operations). Key strengths: • LLM Orchestration: Designed Smart Routers for multi-provider LLM workflows (OpenAI, AWS Bedrock, Groq, Anthropic), including real-time fallback, health monitoring, and load balancing. • LLM Ops: Built fine-tuning and evaluation pipelines with robust failure recovery and dynamic routing. • Monitoring & Reliability: Developed real-time monitoring and alerting with New Relic, Slack, and PagerDuty—including custom retry and escalation logic. • Search & Retrieval: Integrated GCP Custom Search and SERP APIs for intelligent fallback and high availability. • Infra & Deployment: Hands-on with Kubernetes, Docker, and AWS for container orchestration. • Voice Interfaces: Built voice-to-text transcription using WebSocket streaming between JS frontends and FastAPI backends. Passionate about combining AI with robust infrastructure to build production-ready systems that scale. Always exploring smarter, faster, and more resilient ways to solve real-world problems.

Location

Bengaluru

AI stack

claude

cursor

elevenlabs

langchain

langgraph

ollama

Work experience

AI Engineer at Tredence Inc., Jan 2026 - Present · 7 mo, Bengaluru

SDE 1 - Applied AI at Krutrim, Jul 2024 - Jan 2026 · 1 y 6 mo, Bengaluru, Karnataka, India

SDE Intern at Krutrim, Feb 2024 - Jul 2024 · 6 mos, Bengaluru, Karnataka, India

AI Intern at Ola, Aug 2023 - Nov 2023 · 4 mos, Bengaluru, Karnataka, India

Education

Bachelor of Technology - BTech, Computer Science, Presidency University Bangalore

High school, ryan international school

Public links

github: https://github.com/mdsarfraz2002