Skip to content
View karandeepdps's full-sized avatar
💭
I may be slow to respond.
💭
I may be slow to respond.

Block or report karandeepdps

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
karandeepdps/README.md

Karandeep Singh Dhillon

Senior Software Engineer • AI Systems • Backend Platforms • Distributed Processing

I build production-grade AI systems, event-driven platforms, and backend infrastructure
that hold up under real scale, real data, and real operational pressure.

Email LinkedIn Portfolio GitHub

Banner

Profile

Production-focused engineer with 7+ years across fintech, healthcare, computer vision, and applied AI. I work at the intersection of backend systems, ML infrastructure, LLM workflows, and distributed processing.

100M+
records processed in distributed systems
3.5x
throughput improvement at scale
~60%
faster fraud investigation workflows
90%+
model accuracy / specificity in healthcare AI
$200K+
R&D funding supported through technical prototypes
7+
years building production systems

What I Build

LLM Workflows • Agentic Systems • Backend APIs • Internal Platforms
Event-Driven Architecture • Distributed Processing • ML Infrastructure
Fraud / AML Tooling • Healthcare AI • Automation with Real Operational Impact

Experience Highlights

Nasdaq

Built platform and AI systems for financial workflows, including event-driven pipelines, ECS-based distributed processing, internal ML API platforms, and LLM-assisted tooling for AML and fraud investigation teams.

MeddAI Medical

Built backend and ML systems for a healthcare AI platform, including multimodal data pipelines, inference services, compliance-aware architecture, and production workflows for diagnostic use cases.

Earlier Work

Shipped systems across computer vision, edge AI, autonomous navigation, and analytics products, working in both startup and research-heavy environments where reliability mattered as much as experimentation.


Strengths

Systems

  • Distributed systems design

  • Event-driven architecture

  • Scalable APIs and microservices

  • Async processing and messaging

  • Production observability and reliability

AI

  • LLM-powered workflows

  • ML infrastructure and inference

  • Applied machine learning

  • Computer vision systems

  • Automation platforms


Tech Stack

Languages
Python TypeScript Node.js Java SQL Go

Backend
FastAPI Django Flask Express REST APIs OpenAPI Microservices

AI / ML
LLMs Amazon Bedrock PyTorch TensorFlow Computer Vision Deep Learning

Cloud / Infra
AWS ECS Lambda S3 EMR Step Functions Docker Kubernetes Jenkins

Data / Systems
PostgreSQL Redis MongoDB Event-Driven Systems Distributed Processing Async Messaging


Current Focus

  • Building AI systems that are useful in production, not just impressive in demos
  • Designing backend platforms that simplify model deployment and operational workflows
  • Working on infrastructure that scales cleanly under load and stays maintainable

Connect

Pinned Loading

  1. Leaf-Species-Recognition-Challenge-CVDC2020 Leaf-Species-Recognition-Challenge-CVDC2020 Public

    Rank 1 with 5 models Ensembling (Base Resnet50, InceptionV3, MobilnetV2, MyNetwork with D=1,MyNetwork with D=2) and rolling window smoothing of outputs.

    Jupyter Notebook 1

  2. OpenVino-Model-Optimization OpenVino-Model-Optimization Public

    Optimise Keras models using OpenVino

    Python 2

  3. step_size_epsilon_vs_reward_distributio step_size_epsilon_vs_reward_distributio Public

    Ablation study on maximizing the RL reward using hyperparameter tuning.

    Jupyter Notebook

  4. Greedy-Kart Greedy-Kart Public

    Path Planning Using Deep Reinforcement Learning: Soft Actor–Critic

    ASP.NET 2

  5. GENAI GENAI Public

    Generative AI and LLM'S

    Python

  6. Graph-Rag Graph-Rag Public

    Graph-Rag

    JavaScript