AI Engineer · Pittsburgh, PA · Open to work

Anusha
Shiva Kumar

I build AI systems that actually work in production, not just in demos. RAG pipelines, multi-agent orchestration, memory architectures, real-time voice inference — end to end, from research to deployment.

View my work ↓ Download CV Get in touch
About

A little about me

I'm an AI Engineer specializing in building scalable, production-grade intelligent systems. My work sits at the intersection of LLMs, backend engineering, DevOps, and data science, translating research into reliable systems that reduce friction for real people, not just automating tasks, but anticipating needs.

Currently at Mira Copilot, I architect end-to-end pipelines spanning retrieval-augmented generation, multi-agent orchestration, dual-memory architectures, and real-time voice interfaces. I also own the deployment side, cloud infrastructure, containerization, and CI/CD from dev to production.

Before focusing on AI, I sharpened my analytical foundation through data consulting at FedEx Ground (via Katz / KPMG, placing 2nd in the KPMG US Cup) and academic research at the University of Pittsburgh, where I graduated with a 3.9 GPA in Information Science.

5+Production systems
12+Projects shipped
3.9MS GPA, Pitt
2ndKPMG US Cup
Experience

Where I've worked

Oct 2025 — Present Mira Copilot Remote · Full-time

AI Engineer

  • Architected end-to-end RAG pipeline enabling context-aware, multi-turn conversations grounded in user-specific data at scale.
  • Designed dual-memory system separating short-term context from long-term user preferences; built ReAct-style agent with intent classification and tool routing.
  • Integrated real-time STT/TTS pipelines for low-latency voice-first interactions and a calendar intelligence engine with explainable meeting-time ranking.
  • Owns full deployment stack — cloud infrastructure, containerization, and CI/CD from dev to production.
PythonFastAPILangChain RAGPostgreSQLRedis AWSDockerCI/CD
Sep 2025 — Present Product Manager Accelerator Remote · Part-time

AI Software Engineer

  • Designing and shipping production-grade AI products end-to-end — backend, AI infrastructure, and deployment.
  • Built RAG pipelines, LLM orchestration layers, agent-based systems, and memory architectures.
  • Collaborated cross-functionally with PMs, engineers, and researchers from MVP to production.
LLM OrchestrationRAG FastAPIDockerCI/CD
Jul 2024 — Dec 2025 University of Pittsburgh Hybrid · Part-time

Applied Data Scientist (Research)

  • Analyzed 50K+ behavioral and demographic records using SPSS and Python — chi-square, regression, and descriptive modeling.
  • Produced 10+ analytical reports translating complex findings for academic and non-technical audiences.
  • Served as Course Coordinator for the Master's in Data Science program (Aug 2024 – Aug 2025).
PythonSPSS Statistical AnalysisData Visualization
Jan 2024 — Apr 2024 FedEx Ground via Katz / KPMG

Business Data Analyst

  • Led cross-functional analytics for last-mile delivery optimization — drove 15% efficiency improvement and projected 9.8% annual cost savings.
  • Built real-time Tableau dashboards monitoring operational metrics for a team of 7 analysts.
  • Placed 2nd in the KPMG US Cup Competition for strategic innovation.
SQLPython TableauExcelAnalytics
Jan 2022 — Mar 2022 Duke University Remote · Internship

Research Software Developer

  • Built a mobile app for real-time sign language to English conversion in Duke's CS AI research lab.
  • Applied computer vision and gesture recognition to enable accessible communication for the hearing-impaired.
Computer VisionMobile Dev Gesture RecognitionAI Research
Projects

Selected work

01 · 2026 · Active

RewardWise

Full-stack AI travel rewards optimizer that helps users decide when to pay with points vs. cash. Built a deterministic decision engine evaluating loyalty program reward valuations to generate optimal booking recommendations, with FastAPI backend and Next.js frontend.

Next.jsFastAPI DockerCI/CD
02 · 2025 · Production

Mira Voice AI Backend

Core backend for a voice-first AI scheduling assistant. Architected end-to-end RAG pipeline, dual-memory system, ReAct agent orchestration with intent classification and tool routing, real-time STT/TTS streaming, and a calendar intelligence engine with explainable meeting suggestions.

LangChainRAG FastAPIAWS
03 · 2025

Discord RAG Bot

A retrieval-augmented generation bot for Discord that answers questions grounded in custom knowledge sources. Built with Python, integrating vector search and LLM reasoning for accurate, context-aware responses inside Discord servers.

PythonRAG LLMDiscord API
04 · 2024

AI Desktop Assistant

AI-powered desktop assistant built with Python and OpenAI's GPT-4, designed to engage in human-like conversations and perform automated tasks. An early exploration into conversational AI and task automation on local machines.

PythonGPT-4 OpenAI APIAutomation
05 · 2024

Reflections

Full-stack photo gallery platform with user authentication, role-based access control, photo upload and metadata management, commenting, and admin moderation. Focused on responsive, device-friendly UI design.

Node.jsExpress MongoDBBootstrap
06 · 2024 · Award

FedEx Delivery Optimizer

Data analytics consulting project optimizing last-mile delivery for FedEx Ground. Built real-time Tableau dashboards, modeled 15% efficiency improvements, identified 9.8% projected cost savings through volume-density analysis. 2nd place, KPMG US Cup Competition.

PythonSQLTableau
07 · 2022 · Research

Sign Language Translator

Mobile app for real-time sign language to English conversion, built at Duke University's AI research lab. Applied computer vision and gesture recognition to break communication barriers for the hearing-impaired community.

Computer VisionMobileAI
08 · 2022 · Published

HGS Algorithm Research

Led a 4-member team enhancing the Hunger Game Search meta-heuristic algorithm — improving computational speed and mitigating premature convergence. Assessed with k-means clustering. Published in Webology, September 2022.

PythonMLResearch
Skills

What I work with

Languages
  • Python
  • JavaScript / TypeScript
  • SQL
  • HTML & CSS
AI / ML
  • LangChain
  • PyTorch
  • RAG pipelines
  • Agent orchestration
  • LLM fine-tuning
  • MLOps / MLSecOps
Backend & Data
  • FastAPI
  • Node.js / Express
  • PostgreSQL
  • Redis
  • MongoDB
  • REST APIs
Infra & Tooling
  • AWS
  • Docker
  • CI/CD pipelines
  • Tableau
  • SPSS
  • Git
Education

Where I learned

Aug 2023 — May 2025

M.S. Information Science

University of Pittsburgh

GPA: 3.9 · Specialization in AI, data science, and health informatics. Worked as Applied Data Scientist (Research) and Course Coordinator for the Master's in Data Science program.

Aug 2018 — Jul 2022

B.E. Computer Science

Ramaiah Institute of Technology

Published research in optimization algorithms. Led award-winning project team — Best Project at Pradarshana for VR-based physical rehabilitation for cerebral palsy patients.

Contact

Let's talk

I'm open to AI/ML Engineer and Software Engineer roles where I can build things that matter — systems that reduce friction for real people.

Whether you have a role in mind, a collaboration idea, or just want to connect — I'd love to hear from you.