research

Diff-GODiffusion Goal-Oriented Communications

A noise-optimized diffusion framework with Noise-Restricted Forward Diffusion (NR-FD) process for ultra-high bandwidth efficiency semantic communication.

PyTorchDiffusion ModelsLPIPSHPC
research

Diff-GO+Enhanced Generative Feedback Framework

Improved semantic image generation quality through local generative feedback (LGF) with dictionary learning for effective noise codebook design.

PyTorchVQ-VAEDiffusion Models
research

LaMI-GOLatent Mixture Integration Framework

Task-driven latent integration using VQ-Diffusion models and VQGAN for ultra-high bandwidth efficiency while maintaining semantic fidelity.

PyTorchVQ-DiffusionVQ-GAN
research

TACOTask Adaptation and Context Embedding

Vector Quantized VAE for task-driven semantic quantization and imitation learning, improving autonomous driving applications.

PyTorchVQ-VAEImitation Learning
engineering

IgnitionHigh-Performance Transformer Training with CUDA

From-scratch transformer training pipeline with custom CUDA kernels, mixed-precision training, gradient accumulation, and distributed data parallelism with integrated profiling and benchmarking.

PyTorchCUDA C++DeepSpeedAccelerate
engineering

CompassRLHF and DPO Alignment Toolkit

End-to-end alignment toolkit covering the full pipeline from reinforcement learning fundamentals through reward model training, RLHF, and Direct Preference Optimization, with LLM-as-judge evaluation.

PyTorchHuggingFace TRLGymnasiumW&B
engineering

PrismSystematic LoRA/QLoRA Fine-Tuning Framework

Structured framework for parameter-efficient fine-tuning experiments using LoRA and QLoRA, providing reproducible ablation analysis across rank, alpha, quantization, and learning rate configurations.

HuggingFaceLoRA/QLoRAbitsandbytesW&B
engineering

TurbineLLM Inference Optimization and Serving Benchmarks

Comprehensive benchmark suite comparing LLM inference performance across five serving frameworks with structured experiments covering quantization, multi-GPU scaling, speculative decoding, and prefix caching.

vLLMTensorRT-LLMONNX RuntimeTriton
engineering

NexusProduction RAG Engine with Multi-Strategy Retrieval

Production-grade Retrieval-Augmented Generation engine supporting dense, sparse, and hybrid retrieval strategies across multiple vector database backends with cross-encoder reranking and automated RAGAS evaluation.

LangChainFastAPIChromaDBQdrant
engineering

ApertureMechanistic Interpretability for Language Models

Mechanistic interpretability research platform implementing induction head detection, activation patching, concept probing, and sparse autoencoders with custom CUDA kernels and JAX implementations.

PyTorchTransformerLensJAXCUDA C++
engineering

SynapseMulti-Agent Research System Across Frameworks

Multi-agent system implementing research workflows across LangGraph, CrewAI, and MCP frameworks with LangSmith observability, cross-framework evaluation, and comparative analysis of agent architectures.

LangGraphCrewAIMCPLangSmith
engineering

VerdictPluggable LLM Evaluation with CI/CD Integration

Pluggable evaluation framework for large language models supporting custom evaluators, benchmark suites, result storage, and CI/CD integration with automated regression detection.

FastAPIOpenAI APIAnthropic APISQLAlchemy
engineering

OrbitEnd-to-End ML Platform Infrastructure as Code

ML platform infrastructure implementing multi-cloud IaC with Terraform, Kubernetes orchestration for model serving, Helm charts for versioned deployments, and CI/CD pipelines with GitHub Actions.

TerraformKubernetesHelmGitHub Actions
industry

Digital Telco Enabler (ADL-DTE)API Catalog for Telecom Enterprises

Led the API Catalog feature design and implementation, improving development efficiency with scalable backend and frontend solutions for telecom enterprises.

ReactSpring BootMicroservicesREST APIs
industry

CutAndDry Payment SystemeCommerce Payment & Logistics Platform

Robust payment system and reporting tools for a universal eCommerce and logistics platform in the food industry.

JavaScriptNode.jsExpressPostgreSQL