Backend & Search Engineer · Gurugram, IN
I teach machines what people mean — not just what they type. Five years of search platforms and ranking models that stay calm at 25K requests a minute.
Based: Gurugram, IndiaTrade: Search platforms · distributed systemsStack: Java · Spring · Elasticsearch · KafkaBelief: Relevance is empathy at scale
01 — Live · query understanding
I’m not a list of frameworks. I’m the person who needs to know why the third result outranked the first — and can’t sleep until it doesn’t.
Search sits where language meets systems, and that’s exactly where I like to live. Query understanding, ranking models, ingestion pipelines that never sleep — the result is platforms serving 25K+ requests a minute across a 10-million-product catalog that still feel personal.
This is roughly what my systems see when you type. Intent, units, geo, price — pulled out of the words, then re-ranked before you blink.
Lexical match gets you candidates. Semantics, CTR and add-to-cart rate decide who actually deserves the top slot.
02 — Experience
Click a role for the full story
03 — Skills
The stack behind the work
The tools I reach for daily — shaped by five years of search, ranking, and backend systems work.
Search & data
Language & retrieval
Backend
Infra & tooling
04 — Lab
Where I build things that don’t have a brief yet
NaturalQuery
A natural-language-to-Elasticsearch query agent built on a custom MCP server (Java 17, Spring Boot 3.x, official MCP Java SDK).
LTR Rescoring
Experiments with XGBRanker rescore pipelines for search relevance tuning.
Query Understanding
NER + semantic tagging to parse intent from raw search queries.
Some become production features. Some stay internal tools. Some just teach me something.
05 — Writing
From the archive
End-to-end integration of Dynatrace and Grafana using Java
How to integrate Dynatrace, the APM tool, with Grafana — a metric analytics and visualisation suite.
Read →Using Dynatrace API with Postman
Learning the Dynatrace API from Postman — token creation, headers, and pulling host metrics.
Read →Knowledge Extraction in Digit Recognition Using the MNIST Dataset
Exploring how interpretable knowledge can be extracted from models trained on handwritten-digit recognition.
Read →Algorithmic Analysis of an Automatic Attendance System using Facial Recognition
A comparative analysis of detection and recognition pipelines for attendance automation.
Read →06 — Elsewhere
@abhiinav.exe
