Bhavik Mehta

Full Stack Developer & AI Enthusiast

Open to Work

Hi, I'm Bhavik Mehta,
a full-stack developer
shipping AI-native products.

I design, build, and ship end-to-end web products, with AI woven in where it actually moves the needle.

{ 02 } — About

I build things for the web

I'm a full-stack developer and AI enthusiast. I love turning complex problems into clean, elegant products — from pixel-perfect UIs to robust backends and AI-powered features.

1.5+

Years Experience

15+

Projects Shipped

Currently Exploring

▋ AI Agents & LLM Tooling

My Approach

— I write code that's meant to be read, not just executed.

— I treat every product as if it's my own — with full ownership.

— I ship fast, iterate faster, and never sacrifice quality.

What I Believe

Great software is invisible — it just works. I build with the user in mind first, performance second, and aesthetics always.

ReactGitNext.jsVercelTypeScriptRedisPythonKubernetesNode.jsGoDockerTailwindPostgreSQLMongoDBGraphQLFigmaFirebaseVue.js

{ 03 } — Skills

My Toolbox

Technologies I work with daily

Frontend

ReactNext.jsTypeScriptTailwind CSSFramer Motion

Backend

Node.jsExpressPostgreSQLRedisPrisma

AI / ML

OpenAI APILangChainPythonTensorFlowHugging Face

DevOps

DockerAWSVercelGitHub ActionsCI/CD

Tools

FigmaGitPostmanVS CodeLinear

Databases

PostgreSQLMongoDBRedisSupabasePlanetScale

{ 04 } — Experience

Where I've worked

Amdocs

Software Engineer

Sep 2022 – Jul 2024

— Developed billing system features and backend functionalities on AT&T’s enterprise platform in Python and Java, directly serving internal employees and affecting millions in monthly revenue.
— Owned 20+ billing applications across three US regions, independently managing feature releases, production stability, and cross-region deployments end-to-end.

Virtual Math Labs

Software Developer Intern

Aug 2021 – Dec 2021

— Engineered modular backend components using Python and JavaScript by applying OOP principles, data structures, and algorithmic design, resulting in a 20% reduction in defect density across internal testing cycles.
— Built and troubleshot Linux-based backend services by leveraging process management, shell utilities, and containerized deployment workflows, improving system stability across staging environments.

Seattle University — Residential Life

Resident Hall Desk Assistant

Sep 2025 – Jun 2026 · 10 mos

— Served as the first point of contact for 200+ on-campus residents, handling walk-in requests, incident reports, and after-hours escalations with consistent professionalism and follow-through.
— Managed physical resource handovers including room keys, maintenance equipment, and shared collateral, tracking every transaction through sign-out logs to ensure zero loss across the academic year.

Seattle University — International Student Center

International Student Ambassador

Jun 2025 – Jun 2026 · 1 yr 1 mo

— Responded to prospective international students through email, phone, and messaging platforms regarding admissions, immigration documentation, and enrollment steps.
— Developed structured guides and communication templates that simplified complex application procedures for international applicants.

Amdocs

Software Engineer

Sep 2022 – Jul 2024

— Developed billing system features and backend functionalities on AT&T’s enterprise platform in Python and Java, directly serving internal employees and affecting millions in monthly revenue.
— Owned 20+ billing applications across three US regions, independently managing feature releases, production stability, and cross-region deployments end-to-end.
— Diagnosed runtime and service-level failures across Linux environments by analyzing application logs, process behavior, and inter-service dependencies during high-severity production incidents.
— Automated Python and Java regression frameworks integrated into Jenkins CI/CD pipelines, catching 30% more defects before release and enabling faster, more consistent deployments.

JavaPythonLinuxCI/CDBackend

Virtual Math Labs

Software Developer Intern

Aug 2021 – Dec 2021

— Engineered modular backend components using Python and JavaScript by applying OOP principles, data structures, and algorithmic design, resulting in a 20% reduction in defect density across internal testing cycles.
— Built and troubleshot Linux-based backend services by leveraging process management, shell utilities, and containerized deployment workflows, improving system stability across staging environments.
— Optimized cross-layer application performance by debugging API calls, database queries, and inter-service communication, reducing runtime bottlenecks and improving request handling consistency.
— Strengthened release reliability by contributing to peer code reviews, technical documentation, and CI/CD pipelines using Jenkins-style automation, ensuring reproducible builds and structured deployment workflows.

PythonJavaScriptLinuxDockerJenkins

Swipe

{ 05 } — Education

Where I studied

Seattle University

Masters, Computer Science

Sep 2024 – Jun 2026 · Seattle, USA

— Artificial Intelligence
— Distributed Systems
— Machine Learning
— Security in Computing

Savitribai Phule Pune University

Bachelor of Engineering, Information Technology

Jun 2019 – Aug 2022 · Pune, India

{ 06 } — Projects

Selected Work

AI / AWS1ST PRIZE — AWSHacks 2026

May 2026

ARIA - Autonomous Response Intelligent Assistant

Multi-agent AI co-pilot for 911 dispatchers, built on Amazon Bedrock. Six specialized agents (Claude Haiku 3.5 + Claude Sonnet 4) process real-time Amazon Transcribe streaming, run parallel domain watchers in AWS Lambda, and surface a single dispatcher recommendation in under 15 seconds — grounded in FEMA and MPDS protocols via Bedrock Knowledge Base with RAG.

AWS

AI / Agents

Aug 2026 – Sep 2026

Cartograph

Cyclic LangGraph research agent — supervisor → specialist → critic loop that sends weak drafts back for revision, Pydantic-validated output on every hop, served over MCP, with a token auditor that attributes every model call to a cause and reports which tokens were wasted.

SaaS / AI

Apr 2025 – Present

Peekwise.ai

Monorepo competitive intelligence SaaS — BullMQ as the sole async handoff between ingestion, AI enrichment, and orchestration layers; cost-zero Groq pipeline processing ~2,075 reviews/day; Redis-first sub-millisecond dashboard reads.

MQGq

AI / Evals

Aug 2026

RAG Evaluation Harness

Production-shaped RAG pipeline whose answers are measured and gated in CI — retrieval recall, faithfulness, hallucination, refusal on out-of-scope questions, latency, and cost all scored on a labeled test set, with regressions blocking the merge.

ChSTDE

View All Projects →

Full details + bullet breakdowns

Swipe

View All Projects

{ 07 } — Blog