Pfizer logoPfizer Externship via Extern

Early-career professional exploring next steps

I have some work experience and I am building skills and samples to shape my career direction.

Work samples

A compact set of projects and samples that reflect my current skills and the areas I am exploring as I define my career path.

  • Adaptive LLM Router
    Adaptive LLM Router

    Deployed an adaptive multi-LLM routing system, ensuring precise agent state management while dynamically switching models at tool call boundaries across 500+ SWE-Bench Verified software engineering tasks. Created a backend system with modular model adapters, parallel task execution, human-in-the-loop routing, session management, persistent turn history, and real-time tracking of token usage and tool calls. Integrated local Qwen models via vLLM/SGLang along with frontier OpenAI Codex models through an adapter interface, enabling cross provider model switching and context preservation within active agent tasks. Refined automated routing signals from testing data including runtime failures, token usage, dependency errors, and execution progress, reducing token costs by 36% while maintaining task success rate over single model baselines.

    PythonCodexvLLM/SGLangSQLGitHugging FaceAPIs
  • Samsung Solve for Tomorrow
    Samsung Solve for Tomorrow

    Built an XGBoost machine learning pipeline using environmental data, feature engineering, and model evaluation to forecast Lake Superior nearshore wind production. Compared and validated two predictive models, linear regression and gradient-boosted models to assess nearshore wind-farm feasibility, contributing to selection as a Minnesota semifinalist.

    PythonXGBoostMatplotlibPandasNumPy

About me

I have some work experience and I am building skills and samples to shape my career direction.

I am Shivashish Khanna. I have some work experience but I am early in my career and exploring where I want to focus next.

Externships

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

In progress

Experience

Software Development Intern

Minnesota NLP Lab · July 2026 – Present

Firmware Developer

Formula SAE · September 2026 – Present

LLM Research Intern

University of Minnesota - Twin Cities · May 2025 – Oct. 2025

Education

University of Wisconsin–Madison

Bachelor of Science in Computer Science, Mathematics, and Economics · Class of 2029

Skills

Early-career experienceProject workSkill developmentCareer exploration

Adaptive LLM Router

Deployed an adaptive multi-LLM routing system, ensuring precise agent state management while dynamically switching models at tool call boundaries across 500+ SWE-Bench Verified software engineering tasks. Created a backend system with modular model adapters, parallel task execution, human-in-the-loop routing, session management, persistent turn history, and real-time tracking of token usage and tool calls. Integrated local Qwen models via vLLM/SGLang along with frontier OpenAI Codex models through an adapter interface, enabling cross provider model switching and context preservation within active agent tasks. Refined automated routing signals from testing data including runtime failures, token usage, dependency errors, and execution progress, reducing token costs by 36% while maintaining task success rate over single model baselines.

PythonCodexvLLM/SGLangSQLGitHugging FaceAPIs
View all work

Samsung Solve for Tomorrow

Built an XGBoost machine learning pipeline using environmental data, feature engineering, and model evaluation to forecast Lake Superior nearshore wind production. Compared and validated two predictive models, linear regression and gradient-boosted models to assess nearshore wind-farm feasibility, contributing to selection as a Minnesota semifinalist.

PythonXGBoostMatplotlibPandasNumPy
View all work

✅ Verified by Extern · ⏱️ In progress

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.

AI & MLPythonDocument IntelligencePresentation Skills

Overview

The project prototyped an AI-powered document intelligence pipeline that combined OCR, RAG, and LLM components to process enterprise PDFs. The work involved researching generative models, designing a document-processing flow, and producing explanatory materials describing model behavior and integration choices.

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

What I've accomplished

I produced research and explanatory material that clarified how large language models operate and how they fit into an AI document-insights pipeline.

Project breakdown

View all work