Headline

Senior Backend & AI Engineer | Scaled LLM-powered services to 10M+ daily requests | Distributed Systems | Building Conversenow

About

I'm open to Senior / Staff-track Backend, Platform, or production-focused ML/AI Engineer roles — Bangalore-first, remote-friendly globally. If you're scaling backend systems or putting LLMs into real products, let's talk. Senior Backend Engineer with 7 years building and owning high-performance, distributed systems in Go — most of it powering real-time conversational/voice AI at ConverseNow.ai, where my services sit on the critical path of live customer ordering. I work at the intersection of backend systems and production AI: low-latency Go microservices on GCP, plus the LLM tooling, RAG, and fine-tuning pipelines that make models actually reliable in production. I like owning a service end-to-end — SLAs, incidents, redesigns, and all. What I've shipped: Cut cart-generation latency from ~1s to 300ms (70%+) through algorithmic and infrastructure rework on a service in the live ordering path. Migrated a vector database from HTTP/REST to gRPC, handling 10M+ daily requests with materially lower overhead and tail latency. Led the migration from a legacy AI stack to GenAI, reaching feature/quality parity in 6 months. Built a production hybrid RAG service with multi-embedding support and custom re-ranking for measurably better retrieval. Fine-tuned models from ~70% to 90%+ accuracy while cutting inference cost ~20% and halving token consumption via better data, eval harnesses, and prompt/dialog policy work. Designed a multi-LLM integration + benchmarking framework so we could swap and evaluate models fast. Built a CI/CD automation framework that removed ~1 day of manual QA per cycle and raised release confidence. Core stack: Go, gRPC, Python, GCP, Kubernetes, Docker, Pub/Sub, Redis, Qdrant, PostgreSQL, plus LLM/RAG/fine-tuning tooling and observability. I'm open to Senior / Staff-track Backend, Platform, or production-focused ML/AI Engineer roles — Bangalore-first, remote-friendly globally. If you're scaling backend systems or putting LLMs into real products, let's talk.

Location

Greater Bengaluru Area

AI stack

claude code

cursor

Goose

LM Studio

OpenRouter

Qdrant

Work experience

Senior Software Engineer at The Walt Disney Company, Jun 2026 - Present · 3 mos, Bengaluru, Karnataka, India, - Took ownership of LLM observability using data dog and langsmith e2e design of low code agentic system use to create smart agentic workflow

Software Engineer at ConverseNow.AI, Aug 2023 - Jun 2026 · 2 y 10 mo, bengalore

Software Engineer at ConverseNow.AI, Mar 2020 - Aug 2023 · 3 y 5 mo, Bengaluru, Karnataka, India, Cut cart-generation latency from ~1s to 300ms (70%+) through algorithmic and infrastructure rework on a service in the live ordering path. Migrated a vector database from HTTP/REST to gRPC, handling 10M+ daily requests with materially lower overhead and tail latency. Led the migration from a legacy AI stack to GenAI, reaching feature/quality parity in 6 months. Built a production hybrid RAG service with multi-embedding support and custom re-ranking for measurably better retrieval. Fine-tuned models from ~70% to 90%+ accuracy while cutting inference cost ~20% and halving token consumption via better data, eval harnesses, and prompt/dialog policy work. Designed a multi-LLM integration + benchmarking framework so we could swap and evaluate models fast. Built a CI/CD automation framework that removed ~1 day of manual QA per cycle and raised release confidence.

Intern at BSH Home Appliances Group, Jun 2019 - Mar 2020 · 10 mos, Greater Bengaluru Area

Education

Computer Programming, Scaler

Bachelor of Technology, Electronics and Communications Engineering, Lovely Professional University