DK Dev Kumar

Full Stack GenAI - FastAPI, Angular, RAG, secure SDLC

GenAI products built for regulated workflows and real users.

I build secure full-stack GenAI systems that pair Python/FastAPI and Java/Spring Boot services with Angular and TypeScript frontends, RAG pipelines, embedding retrieval, CI/CD quality gates, and accessible experiences for enterprise and regulatory teams.

Engineering
View Projects GitHub LeetCode
0 % recommendation accuracy lift
0 K+ monthly requests processed
0 % post-deployment defect reduction
0 % manual processing reduction

Regulatory GenAI Focus

Useful GenAI in regulated environments needs secure interfaces, grounded retrieval, auditability, and accessible delivery from the first design pass.

01

Ground the answer

RAG workflows, embeddings, source citations, prompt templates, retrieval ranking, and evaluation sets keep generated output tied to evidence.

02

Protect the workflow

OWASP Top 10, LLM guardrails, secrets management, least-privilege IAM, audit logs, and secure SDLC make sensitive workflows safer to ship.

03

Build the whole product

Angular, TypeScript, responsive UI, WCAG-aware patterns, FastAPI, Spring Boot, REST APIs, and event-driven services connect model value to users.

04

Prove every release

GitHub Actions, GitLab CI, Jenkins, Docker, Kubernetes, unit, integration, and E2E tests turn GenAI features into controlled production changes.

Architecture Diagram

A full-stack GenAI platform from accessible Angular UI to secure APIs, RAG orchestration, data stores, guardrails, audit logs, and CI/CD gates.

Regulatory full-stack GenAI architecture Regulatory users interact with an Angular UI, API gateway, FastAPI and Spring Boot services, RAG orchestration, vector and document stores, LLM guardrails, audit logs, and CI/CD quality gates. Regulatory Users analysts auditors business teams Angular UI TypeScript WCAG patterns Quality Gates tests + security Docker deploys GenAI Services FastAPI + Spring Boot RAG orchestration LLM guardrails Knowledge Layer documents vector search Data Stores PostgreSQL MongoDB / Redis Audit Trail lineage logs policy evidence accessible first grounded responses auditable delivery

Technical Stack

Full-stack, GenAI, cloud, data, security, testing, containers, and accessibility practices.

Python FastAPI Java Spring Boot RESTful APIs microservices Node.js Angular TypeScript JavaScript HTML5 CSS3 WCAG React OpenAI APIs LangChain RAG workflows embeddings prompt engineering GitHub Actions GitLab CI Jenkins Docker Kubernetes Jest Jasmine JUnit PyTest AWS Lambda ECS S3 RDS SQS SNS EventBridge Step Functions PostgreSQL MongoDB Redis Kafka OWASP Top 10 least-privilege IAM

Professional Experience

Full work history with every impact bullet from the resume.

Mar 2025 - Present Sprouts AI Software Engineer (Full Stack + GenAI) | Chicago, IL
  • Built production Generative AI application backend in Python/FastAPI integrating OpenAI APIs, RAG workflows, and embedding-based matching - boosting recommendation accuracy 35% for regulatory-style hiring and compliance workflows.
  • Developed responsive TypeScript frontend components with accessibility-first patterns, collaborating cross-functionally with product, ML, security, and business teams to translate requirements into shipped features.
  • Implemented CI/CD pipelines (GitHub Actions, PyTest, Docker) with automated unit and integration testing, embedding code quality and security hygiene (secrets management, least-privilege IAM) into delivery.
  • Adopted AI-assisted development tools (GitHub Copilot, Cursor) responsibly while maintaining code quality standards - accelerating feature delivery 40% across Python and TypeScript codebases.
Aug 2023 - Mar 2025 Resilience Inc Software Engineer (Full Stack) | Chicago, IL
  • Built and maintained full-stack applications on Node.js/TypeScript backend and modern frontend (React + Angular components) with RESTful APIs supporting data analysis and reporting workflows for 10K+ users.
  • Designed AWS-managed serverless architecture (Lambda, S3, RDS, SQS) for production web product, processing 500K+ monthly requests at 99.9% uptime with event-driven messaging patterns.
  • Implemented GitHub Actions CI/CD with Jest unit, integration, and E2E testing and Docker containerized deployment - reducing post-deployment defects 50% across cross-functional product teams.
  • Applied OWASP Top 10 principles, secrets management, and least-privilege IAM across backend services, partner integrations, and CI/CD pipelines.
Apr 2018 - Aug 2023 Tata Steel Software Engineer (Full Stack, Java + Angular)
  • Architected and shipped enterprise full-stack applications on Java/Spring Boot RESTful APIs and Angular/TypeScript frontend (MEAN stack) for regulatory training, compliance, and reporting workflows - cutting manual processing 60%.
  • Built cloud-native Java microservices on Docker and Kubernetes with PostgreSQL and Kafka event-driven messaging - achieving 40% API response improvement and 99.99% uptime in production.
  • Established Jenkins-based CI/CD pipelines with JUnit and integration testing, containerized deployment, and application security (OWASP, secrets management, least-privilege) across frontend and backend teams.
  • Spearheaded Agile SDLC and code review standards across a cross-functional team, mentoring engineers on accessible, responsive UI patterns and secure full-stack delivery.

Selected Projects

GenAI agents, RAG apps, financial insights, distributed systems, systems programming, and product builds with demo and source links.

AI Agent LangChain

LangChain Chat with Search

LangChain-based conversational AI agent integrating LLM APIs with web-search and Wikipedia tool calling, showing model integration and prompt patterns.

Source Code
Agentic RAG Node.js + AWS

AskMyStore

Production agentic RAG application with LLM API integration, serverless AWS backend, DynamoDB, and TypeScript responsive frontend.

Demo Source Code
AI Financial Insights Full Stack

TradeSentinel

Full-stack TypeScript platform with OpenAI-powered analysis and serverless REST APIs for financial market workflows in a regulated-data domain.

Demo Source Code
Event Pipeline Java + Kafka

Real-time Stock Market Analysis Pipeline

Distributed event-driven pipeline for real-time financial data ingestion and processing with scalable backend and messaging patterns.

Source Code
Low Latency C++

CME MDP 3.0 Multicast Feed Handler

Multi-threaded market data feed handler demonstrating high-throughput financial message processing, reliability, and performance discipline.

Source Code
Operating Systems C

Experimental Operating System

Custom OS kernel with scheduling, memory management, and device driver concepts that strengthen backend runtime judgment.

Source Code
Linux Kernel C

Character Device Driver

Linux character device driver project showing kernel-facing C development, interface design, and debugging discipline.

Source Code
Computer Architecture Hardware

16-Bit RISC Processor

Hardware lab project implementing processor fundamentals and reinforcing performance, correctness, and data movement discipline.

Source Code
Application Build Web

STRANGERS

Interactive application project focused on maintainable product delivery, backend integration, and end-to-end implementation discipline.

Source Code
IEEE Publication ML Research

Comparative Study of Movie Recommendation Systems

Published IEEE research comparing collaborative, content-based, and hybrid recommendation models with feature engineering and improved error functions.

Paper Source Code Certificate
iOS App Swift

Pitch Perfect

iOS application demonstrating product execution, media handling, and mobile app fundamentals.

Source Code

Education & Publication

A computer science foundation backed by full-stack systems, applied AI, and published research.

Graduate Study

Illinois Institute of Technology

M.S., Computer Science

Undergraduate Study

National Institute of Technology, Calicut

B.Tech, Computer Science

Publication

IEEE Research

Comparative Study of Movie Recommendation Systems using Feature Engineering.

Read Paper

Contact

Secure full-stack GenAI, regulatory workflows, accessible UI, and production backend delivery.

Dev Kumar | Chicago, IL | +1-312-532-8223 | devkumar.dklv@gmail.com

Email GitHub LeetCode