# Pranav Sastry Resume

Canonical URL: [/resume/ps-com-resume](https://pranavsastry.com/resume/ps-com-resume)

## Site Chrome

- Brand: [Pranav Sastry](https://pranavsastry.com/)
- Current route: [/resume/ps-com-resume](https://pranavsastry.com/resume/ps-com-resume)

### Textual Menu

- [Home](https://pranavsastry.com/llms.txt)
- [Projects](https://pranavsastry.com/projects/llms.txt)
- [Papers](https://pranavsastry.com/papers/llms.txt)
- [Posts](https://pranavsastry.com/posts/llms.txt)
- [Career](https://pranavsastry.com/career/llms.txt)
- [News](https://pranavsastry.com/news/llms.txt)


## Resume Metadata

- Description: AI engineering, agentic systems, and applied machine learning research in a compact, ATS-readable PDF.

## Resume Content

### Profile

- Name: Pranav Sastry
- Headline: AI Engineer - Agentic Systems and Applied Research
- Location: Bengaluru, Karnataka, India

- Contact: [pranavsastry.com](https://pranavsastry.com)
- Contact: [github.com/pranftw](https://github.com/pranftw)
- Contact: [linkedin.com/in/pranftw](https://www.linkedin.com/in/pranftw/)
- Contact: [pranava.sri@gmail.com](mailto:pranava.sri@gmail.com)

AI engineer building production agentic systems, code-generation workflows, and applied machine-learning research.

### Skills

- **Languages:** Python, TypeScript, JavaScript, C, Bash

- **Frameworks:** PyTorch, PyTorch Lightning, Vercel AI SDK, Next.js, Flask, FastAPI

- **Interests:** Agentic AI, retrieval-augmented generation, efficient deep learning, large language models, API development

### Education

#### BMS College of Engineering

- Degree: Bachelor of Engineering
- Field: Computer Science
- Location: Bengaluru
- Dates: Aug 2019 – Jun 2023

### Experience

#### Sarvam AI

- Role: AI Engineer
- Location: Bengaluru
- Dates: Jan 2026 – Jun 2026

- Built pipelines and frameworks to **automatically optimize agentic harnesses**.
- Developed **code-generation agents** for custom coding workflows.
- Scaled scraper-authoring agents to generate scrapers on demand through the Model Context Protocol (MCP).

#### Sarvam AI

- Role: AI Engineering Intern
- Location: Bengaluru
- Dates: Jul 2025 – Jan 2026

- Led an agentic scraper-generation system that reduced authoring time from three hours to 15 minutes, a **92% reduction** across **four clients**.
- Architected **subagent isolation** to prevent context corruption and enable reliable code generation.
- Implemented automated API detection through runtime testing, then extended the framework to web automation and browser-operator agents.
- Deployed production workflows with Google Cloud Platform (GCP) Cloud Workflows and Cloud Scheduler.

#### Lossfunk

- Role: AI Resident, Founding RecLLM
- Location: Bengaluru
- Dates: Apr 2025 – Jul 2025

- Founded **RecLLM**, an agentic recommendation system for conversational product discovery.
- Built adaptive memory to retain user preferences across long-running interactions.
- Shipped a production-ready Shopify prototype with automatic item indexing after validating business pain points.

#### Indian Institute of Science

- Role: Research Assistant
- Location: Bengaluru
- Dates: Sep 2023 – Apr 2025

- Led an IBM Research collaboration on time-series imputation and developed a novel MLP Mixer architecture.
- Improved on state-of-the-art results by **21%** with a **12K-parameter** design and constant rather than quadratic parameter growth.
- Co-developed a self-diagnosing bias-mitigation framework using Neural Tangent Kernel attribution, vision-language model descriptions, and CLIP embeddings, improving worst-group accuracy by **10.6%**.

#### Indian Institute of Science

- Role: Research Intern
- Location: Bengaluru
- Dates: Jan 2023 – Sep 2023

- Co-designed a weak-supervision architecture combining a generative adversarial network, classifier, and label model, improving label accuracy by **3%** and Fréchet Inception Distance by **seven points**.
- Built an OpenReview literature-survey tool and an automated experiment-management framework.

#### CryptoRelief

- Role: Python Developer
- Location: Bengaluru
- Dates: May 2021 – Jul 2021
- Link: [https://github.com/cryptorelief](https://github.com/cryptorelief)

- Built APIs and SHA-256 search for COVID-19 resource tracking, delivering **90% faster retrieval** for intensive-care, oxygen, and ambulance data.
- Created web scrapers and a Twitter bot for rapid information dissemination.

### Publications

#### ELITS: Efficient Lightweight Imputation for Time Series

- Year: 2026
- Authors: Pranav Sastry, Kalyan Reddy, Sumanta Mukherjee, Vijay Ekambaram, Pankaj Dayama, and Prathosh AP
- Venue: AAAI 2026 Workshop on AI for Time Series Analysis

#### Feature-Guided Subset Selection: Mitigating the Impact of Spurious Features via Data Attribution

- Year: 2025
- Authors: Kumar Shubham, Pranav Sastry, and Prathosh AP
- Venue: NeurIPS 2025 Workshop on Reliable ML from Unreliable Data

#### Fusing Conditional Submodular GAN and Programmatic Weak Supervision

- Year: 2024
- Authors: Kumar Shubham, Pranav Sastry, and Prathosh AP
- Venue: AAAI Main Technical Track 2024
- Link: [https://ojs.aaai.org/index.php/AAAI/article/view/29423](https://ojs.aaai.org/index.php/AAAI/article/view/29423)

#### Performance Analysis of Object Detection Algorithms for Waste Segregation

- Year: 2023
- Authors: Naman Singh, Pranav Sastry, Niharika B. S., Arka Sinha, and Umadevi V.
- Venue: IEEE ICAISE 2023
- Link: [https://ieeexplore.ieee.org/abstract/document/10073863/](https://ieeexplore.ieee.org/abstract/document/10073863/)

### Selected Projects

#### Agentic Scraper Authoring System

- Context: Sarvam AI

- Generated and runtime-validated production scrapers from natural-language requirements, using network monitoring to discover backend APIs for bulk execution.

#### Time-Series Imputation

- Context: IBM Research

- Designed parallel MLP Mixers that improved on state of the art by **21%** with **858× fewer parameters**.

#### Weak Supervision

- Context: Indian Institute of Science

- Unified a generative adversarial network, classifier, and label model, improving label accuracy by **3%** and Fréchet Inception Distance by **seven points**; published at AAAI 2024.

#### Data Attribution for Spurious Correlations

- Context: Indian Institute of Science

- Combined Neural Tangent Kernel attribution, vision-language descriptions, and CLIP embeddings to improve worst-group accuracy by **10.6%**.

#### Object Detection for Waste Segregation

- Context: Engineering Major Project
- Link: [https://github.com/pranftw/oddgen](https://github.com/pranftw/oddgen)

- Co-led YOLO model design and built ODDGen to synthesize hundreds of thousands of annotated images; published at IEEE ICAISE 2023.

#### Aiter: Terminal AI Chat with Multi-Agent Support

- Link: [https://github.com/pranftw/aiter](https://github.com/pranftw/aiter)

- Built modular multi-agent chat with MCP integration, persistent sessions, and extensible agent scaffolding.

#### Neograd: Deep Learning Framework from Scratch

- Link: [https://github.com/pranftw/neograd](https://github.com/pranftw/neograd)

- Built and published a pure-Python automatic-differentiation framework with broadcasting, custom operations, and gradient checking.

#### Web Development and APIs

- Built an [OpenReview paper scraper](https://github.com/pranftw/openreview_scraper), React post editor, bilingual [Flask website](https://gururajhr.com), [Twitter API bot](https://github.com/pranftw/twttr-bot), and [GitIt](https://github.com/pranftw/gitit) for GitHub automation.