Ashish Kumar

Software Engineer

Gurugram, Haryana, India4 yrs 10 mos experience

AI EnabledAI ML Practitioner

Key Highlights

Delivered high-impact systems at Amazon driving 55% increase in attach rates.
Designed and deployed a RAG-powered AI Slack bot for real-time support.
Led projects on dynamic configuration management and AWS optimizations.

Stackforce AI infers this person is a Backend-heavy Fullstack Engineer in Fintech and AI sectors.

Contact

ashish.14spt@gmail.com LinkedIn

Skills

Core Skills

Generative AiMicroservices

Other Skills

Retrieval-Augmented Generation (RAG)Vertex AILangChainRedisFastAPIDockerLow-Level DesignSpring FrameworkVector DatabasesGoogle Cloud Platform (GCP)Spring BootLeadershipHigh level designQA TestingScala

About

Connect 1:1 with me at https://topmate.io/ashish_kumar14 Software Engineer with 4 years of experience in building scalable distributed systems, fintech platforms, and Generative AI solutions. Previously at Amazon (SDE1 & Intern) where I delivered high-impact systems like the Differential Instant Discount Engine, driving a 55% increase in attach rates. At Porter, I worked as an SDE2, leading projects on dynamic configuration management, AWS X-Ray optimizations, and large-scale backend systems. Recently, I designed and deployed a RAG-powered AI Slack bot integrating Vertex AI, LangChain, Redis, and FastAPI, providing real-time engineering support with automated Jira escalations. I thrive in high-pressure environments, enjoy driving projects end-to-end, and am passionate about emerging tech (AI, blockchain, and data-driven innovation).

Experience

4 yrs 10 mos

Total Experience

2 yrs 2 mos

Average Tenure

6 mos

Current Experience

Oracle

Senior Member of Technical Staff

Dec 2025 – Present · 6 mos · Bengaluru, Karnataka, India · Hybrid

Working on AI Data Platform

Porter

SDE 2

May 2025 – Dec 2025 · 7 mos · Bengaluru, Karnataka, India · On-site

> Built a Generative AI conversational bot using RAG (Vertex AI, LangChain, Redis, FastAPI, Docker) to provide real-time, context-aware engineering support. Automated knowledge ingestion from Notion (parsing, chunking, embeddings with text-embedding-004, vector DB indexing) for zero-touch updates and seamless knowledge refresh.
> Designed an intelligent Slack UX with live feedback, source-linked answers, and AI-powered Jira escalation with auto team routing. Enhanced observability by integrating Prometheus & Datadog APM, and deployed the system as an async, scalable, production-ready service.

Generative AIRetrieval-Augmented Generation (RAG)

Amazon

2 roles

SDE 1

Aug 2021 – May 2025 · 3 yrs 9 mos

> Worked on microservices responsible for the entire lifecycle of Rewards, from voucher creation to discovery on the Checkout page, post-checkout coverage calculation, and accounting.
> Contributed to over four major events, such as Prime Day and Great Indian Sale, gaining experience in service operational review, scaling calculations, horizontal scaling, and meticulous monitoring of performance metrics and graphs.
> Got opportunity to own and build industry-first solution to enable variable Instant discounts based on EMI tenure.
> Worked on services responsible for ingesting invoices from shipment carriers, parsing them, and validating the bill amounts before sending them for further payment processing.
> Led campaign to get outdated softwares causing security risks and hosts OS upgraded across multiple teams.

Low-Level DesignSpring FrameworkMicroservices

SDE Intern

Jan 2021 – Jul 2021 · 6 mos

> Owned and built end to end solution to migrate existing static configurations in service package to AWS AppConfig reducing config change time from 2 days to less than 3 hours.
> Implemented an AWS CDK Pipeline for configuration management, enabling code review processes and directory-based storage of configs to enhance maintainability.

Low-Level DesignMicroservices