AI Engineer  ·  Tempe, Arizona

Swathi
Gudivada

Building production-grade Generative AI: RAG pipelines, multi-agent architectures, and real-time ML systems that scale.

Scroll

// about me

AI systems,
built to last.

I'm an AI Engineer pursuing my Master's in Computer Science at Arizona State University (GPA 3.89), specializing in the full stack of modern Generative AI, from vector retrieval and agent reasoning to cloud deployment and observability.

My work spans multi-modal emotion recognition, agentic voice pipelines, MLOps platforms, and RAG hallucination detection. I care deeply about systems that are reliable, measurable, and actually ship.

Currently building at ASU's RVCoLab MIX Center, where I design GenAI pipelines that power AI-driven virtual avatars in real time.

3.89
GPA at ASU
3+
Years in AI/ML
1
Granted Patent
92%
Best Model Accuracy

// technical skills

The toolkit.

Gen AI & Agentic
LangChainLlamaIndexGPT-4o ClaudeGeminiRAG Pipelines Multi-AgentReAct AgentsFAISS ChromaFine-TuningPrompt Eng.
ML & Data Science
TensorFlowPyTorchScikit-learn OpenCVMLflowPySpark PandasNumPyKeras TableauPower BIPlotly
Cloud & DevOps
AWSAzureGCP DockerKubernetesGit GitHub
Languages & Backend
PythonSQLJavaScript C++RBash FastAPIFlaskMongoDB MySQLRESTful APIs

// experience

Where I've built.

AI & Data Engineer Feb 2026 – Present
RVCoLab, MIX Center at Arizona State University · Tempe, AZ
  • Deployed a multimodal emotion recognition system combining computer vision (OpenCV, DeepFace) and biometric signals (EEG, GSR) for real-time adaptive AI avatar behavior.
  • Built an end-to-end agentic voice pipeline (ASR → LLM → TTS) with LangChain tool orchestration enabling autonomous, context-aware responses.
  • Designed scalable GenAI data pipelines (ingestion → feature engineering → inference → LLM output) with MLflow tracking and FastAPI deployment.
  • Integrated real-time generative content via Stable Diffusion, reducing manual content creation effort by 40%.
Grader, AI/ML Capstone Aug 2025 – Dec 2025
School of Computing and Augmented Intelligence (SCAI) at ASU
  • Evaluated 20+ production-grade AI systems focusing on RAG pipelines, LLM integration, and system design quality.
  • Identified systemic failure patterns (hallucinations, poor retrieval, missing evaluation frameworks) and delivered actionable feedback.
Graduate Services Assistant Oct 2024 – Jul 2025
School for Engineering of Matter, Transport and Energy (SEMTE) at ASU
  • Processed and structured 5,000+ microscopy images using OpenCV and NumPy, improving data quality by 25%.
  • Developed CNN-based ML models for microstructure classification, improving prediction accuracy by 16%.
  • Deployed production-ready ML pipeline (TensorFlow, Scikit-learn, FastAPI) achieving 92% accuracy in material property prediction.
AI Intern May 2022 – Jun 2022
PECS (Microsoft Affiliated) · Delhi, India
  • Built a recommendation system using decision trees and clustering, improving student application efficiency by 13%.
  • Developed Flask + SQL Server backend APIs serving personalized recommendations, increasing platform adoption.
ML Intern Aug 2020 – Sep 2020
Smart Knower · Delhi, India
  • Optimized ML models using TensorFlow and PyTorch, improving predictive accuracy by 10%.
  • Built scalable training workflows on AWS, reducing model training time significantly.

// projects

Things I've shipped.

01

HabitFlow × NudgeOps

Full-stack MLOps platform for personalized habit optimization. Contextual multi-armed bandit system (Thompson Sampling) using 14 behavioral features over 30-day windows to dynamically select personalized interventions.

FastAPIPostgreSQLReact RedisCeleryThompson Sampling
02

RAG Hallucination Firewall

Low-latency RAG validation system achieving <162ms retrieval across 198 research papers. Multi-stage hallucination detection pipeline (entropy + divergence + NLI) with evaluation dashboards for systematic debugging.

LangChainFAISSNLIEntropy
View project →
03

GenAI Multi-Agent Workflow

Multi-agent LLM system with ReAct-based reasoning loops, tool integration (search, code execution, file I/O), and persistent vector memory for multi-session context. Reduced manual review effort by 30–40%.

ReActLLMVector DBTool Use
04

Speech Recognition: Deep Learning

Benchmarked 5 deep learning architectures on 100K+ audio samples, achieving 92.1% accuracy with 12ms inference latency. Robust MFCC preprocessing pipeline for generalization across noisy environments.

Deep LearningMFCCAudio ML
View paper →
05

Dermatology Diagnosis Chatbot

MobileNetV2 trained on 12K dermoscopy images across 8 disease classes with 95% diagnostic accuracy. Co-authored a granted patent (IND 102069, Sept 2022). MC Dropout for uncertainty estimation improved generalizability by 18%.

MobileNetV2MC DropoutOpenCVPatented

// education

The foundation.

Master of Science in Computer Science
Arizona State University
Tempe, AZ  ·  Jan 2024 – Dec 2025
GPA 3.89 / 4.0
B.Tech in Artificial Intelligence
Amity University
Noida, India  ·  Aug 2019 – May 2023
GPA 3.5 / 4.0

// contact

Let's build something.

Open to AI/ML engineering roles, research collaborations, and interesting conversations about agentic systems.

sgudiva3@asu.edu