// Software Development Engineer · Amazon

Siddartha
Darisi

I build RAG infrastructureMLOps automationcloud architectureRAG infrastructure
that makes AI reliable at enterprise scale.
Seattle, WA

// About

I'm a Software Development Engineer at Amazon in Seattle, on the AWS Quick RAG team — building high-throughput ingestion pipelines for Amazon Quick Suite, Q Business, and Kendra that process 10,000+ documents a day and power RAG and LLM experiences over enterprise data.

Before Amazon, at People Tech Group I built GenAI-driven MLOps that turn natural-language prompts into validated Infrastructure-as-Code, and an AI/ML document pipeline for HCA Healthcare. I hold an MS in Cyber Security & Privacy (NJIT) and four certifications — two AWS Associate, CompTIA Security+, and CEH v12 — and I'm currently deepening my AI/ML expertise through graduate study at Indiana Wesleyan University.

I mentor engineers on GenAI and DevOps practices. My north star: reliable, responsible AI at enterprise scale.

docs/day processed by pipelines I build at Amazon
0k+
docs/day processed by pipelines I build at Amazon
certifications — AWS ×2, Security+, CEH v12
0
certifications — AWS ×2, Security+, CEH v12
graduate programs — MS Cyber Security + AI/ML (in progress)
0
graduate programs — MS Cyber Security + AI/ML (in progress)
engineers mentored in GenAI & DevOps
0
engineers mentored in GenAI & DevOps

Personal Value Proposition

As a software engineer specializing in cloud architecture and AI/ML systems, I help organizations turn raw enterprise data into intelligent, production-grade products. From high-throughput ingestion pipelines processing 10k+ documents a day to GenAI-driven MLOps that cut release cycles by 35%, I build the infrastructure that makes AI dependable at scale — and I share what I learn by mentoring engineers and publishing hands-on resources like the ones in this portfolio.

// Target audience · Written for AI/ML hiring managers and technical recruiters evaluating my work, engineering collaborators and mentees, and fellow AI/ML practitioners and learners.

// Experience

2024 — Present

Software Development Engineer

Amazon · Seattle

AWS Quick RAG team — high-throughput ingestion for Quick Suite, Q Business, and Kendra: 10k+ docs/day, zero-downtime re-ingestion, 60% faster ML deployments.

RAGAWSLLM IntegrationCI/CD

Apr — Oct 2024

Cloud Engineer

People Tech Group · Seattle

GenAI-driven MLOps turning natural-language prompts into validated IaC (35% faster releases); AI document pipeline for HCA Healthcare cutting manual entry 80%+.

GenAIIaCMLOpsHealthcare AI
Full résumé & skills

// Portfolio Artifacts

View all →
01

The Applied AI Brief — A Published Industry Column

A published AI industry column with three issues live — plus the double-opt-in email platform behind it: Lambda, DynamoDB, and SES on a dedicated AWS account, deployed by OIDC with no stored credentials.

Technical WritingAWS ServerlessEmail Infrastructure
02

Haven — Anatomy of a Listening Machine

A fully local AI therapy companion — QLoRA fine-tuned Llama, a trained 28-emotion classifier, retrieval-grounded answers, and hands-free voice — every step of the ML lifecycle on an 8 GB laptop GPU. Interactive build log with demo video on its page.

LLM Fine-TuningQLoRAApplied ML
03

The Climate of Machine Intelligence

Interactive AI/ML history timeline (1943–2025) charting booms, winters, and thaws — 40 milestones, era barometer, and a log-scale training-compute visualization.

AI/ML ResearchData VisualizationTypeScript
04

Triage Copilot — On-Call AI Assistant

An AI agent that advises but never executes — it questions its way to a hypothesis for a failed AWS pipeline and refuses to guess. Built for a 3am page. Live demo on its page.

AI AgentResponsible AIAWS Operations
05

Machine Learning vs. Deep Learning — A Decision Framework

One question decides between them: can a human write the predictive features down in advance? Two case studies — telecom churn and diabetic retinopathy — where the losing approach was actually tried.

Applied ResearchML vs DLCase Studies
06

PrepPilot — AI Mock Interview Tutor

A local-first AI interviewer that listens to how you speak, not just what you say — a full voice loop (VAD → Whisper STT → prosody analytics → LLM coaching → TTS) running on an 8GB laptop GPU. Demo video on its page.

Full-Stack AISpeech & Audio MLLocal-First LLM

// The Applied AI Brief

View all →

Let's build something intelligent

Open to conversations with recruiters, collaborators, and fellow builders about AI/ML, cloud infrastructure, and MLOps.

or ask my AI assistant — the chat bubble in the corner

AWSAmazon BedrockPythonJava · Spring BootTypeScriptPyTorchTensorFlowKubernetesDockerTerraformReactNode.jsCI/CDRAG SystemsMLOpsAWSAmazon BedrockPythonJava · Spring BootTypeScriptPyTorchTensorFlowKubernetesDockerTerraformReactNode.jsCI/CDRAG SystemsMLOps