# Prachi Patel

Prachi Patel is a remote worker on Himalayas, Senior Applied Scientist at Microsoft, based in United States.

Source: https://himalayas.app/@prachipatel6

```text
Applied scientist at Microsoft building GitHub Copilot CLI’s auto-approve feature, from classifier and evaluation to launch criteria.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | United States |
| Authorized to work in | United States |
| Salary expectations | 60k+ USD |
| Job categories | Machine Learning Engineer, Machine Learning Researcher |
| Skills | Applied Machine Learning, Large Language Models, Classifier Design, Offline Evaluation, Online Evaluation, Agentic Workflows, Signal Processing, RAG, Red Teaming, Prompt Engineering, Telemetry, Experimentation, LoRAs, QLoRA, Supervised FineTuning |

## About

```text
At Microsoft, I lead the science and technical work for GitHub Copilot CLI’s auto-approve feature. I own its system architecture, classifier, evaluation, and telemetry, and serve as the technical DRI for launch criteria and rollout.

At Splunk / Cisco, I architected the Investigation Report skill for the Security AI Assistant, lifting its skill rating from 3.0 to 4.5 out of 5. I also designed dynamic query routing and served as tech lead for an agentic workflow automation engine.

My work spans applied AI and speech research. At Lightbird, I led speech and text features for a conversational AI product and fine-tuned Whisper for a 25% quality gain over the base model; at Columbia University, I research neural mechanisms of speech processing and teach graduate Generative AI.
```

## Experience

### Senior Applied Scientist (current)

[Microsoft](https://himalayas.app/companies/microsoft). Mar 2026 - Present

```text
Lead scientist and tech lead for the auto-approve feature in GitHub Copilot CLI, owning system architecture, classifier, evaluation, and telemetry, and serving as technical DRI for launch criteria and rollout.
```

Skills: Machine-Learning, LLM, GitHub-Co-Pilot, System-Architecture, Evaluation, Telemetry, Python, PyTorch

### Adjunct Professor (current)

[Columbia University](https://himalayas.app/companies/columbia-university-in-the-city-of-new-york)

```text
Develop and teach a graduate curriculum on Generative AI, covering LLM fundamentals, fine tuning, and responsible model use. Design coding assignments and mentor students in building transformer based applications.
```

Skills: Generative-AI, LLM, Fine-Tuning, Teaching, Mentorship, Transformers

### Senior Machine Learning Engineer

Splunk / Cisco. Jun 2024 - Mar 2026

```text
Architected and delivered the Investigation Report skill for the Security AI Assistant, designing a LangGraph workflow that improved skill rating and drove analyst adoption. Designed orchestration graphs for dynamic query routing and served as tech lead for the SOAR agentic workflow automation engine.
```

Skills: LangGraph, LLM, AI-Security, Orchestration, Agentic-Workflows, PyTorch, DDP, Time-Series, Python

### Machine Learning Engineer

Lightbird. Sep 2023 - May 2024

```text
Led speech and text features for a conversational AI product, including transcription, sentiment analysis, named entity recognition, and intent recognition. Fine tuned Whisper for ASR with LoRA and QLoRA, delivering a 25% quality gain over the base model.
```

Skills: Speech-Processing, ASR, Whisper, LoRAs, QLoRA, BERT, Sentiment-Analysis, NER, Intent-Detection

### Machine Learning Research Intern

[Microsoft](https://himalayas.app/companies/microsoft). Mar 2023 - Jun 2023

```text
Developed and served deep learning models for multimodal empathetic prompting of LLMs, yielding one patent. Fine tuned HuBERT and Wav2Vec2 for speech emotion detection and distilBERT for text sentiment, wrapping models in a Python service exposed as generative AI APIs.
```

Skills: Deep-Learning, LLM, HuBERT, Wav2Vec, DistilBERT, Python, Generative-AI

### Applied Scientist II Intern

[Amazon](https://himalayas.app/companies/amazon). Feb 2022 - Dec 2022

```text
Owned the wearable prototype from data collection through classifier, combining signal processing, auditory attention decoding, and classifiers, yielding three patents. Built out an HCI lab from scratch for EEG, EMG, EOG, and pupillometry acquisition, designing experimental protocols and running them with 20+ participants.
```

Skills: Signal-Processing, ICA, SVM, LDA, EEGNet, EEG, EMG, EOG, Pupillometry, HCI, HRTF

### Graduate Research Assistant

[Columbia University](https://himalayas.app/companies/columbia-university-in-the-city-of-new-york). Jan 2017 - Dec 2022

```text
Proposed and ran experiments uncovering neural mechanisms of spatial speech processing in the human brain. Analyzed time series neural data with PCA, clustering, classifiers, linear regression, and Canonical Correlation Analysis.
```

Skills: Neural-Data-Analysis, PCA, Clustering, LDA, SVM, Linear-Regression, CCA, Signal-Processing

## Education

### Columbia University

Doctor of Philosophy, Electrical Engineering

```text
Doctor of Philosophy in Electrical Engineering, applying machine learning and signal processing to uncover neural mechanisms of speech processing in the human brain.
```

### Columbia University

Master of Science, Electrical Engineering

```text
Master of Science in Electrical Engineering with coursework in machine learning, deep learning, signal processing, and related topics.
```

### Nirma University

Bachelor of Technology, Electronics and Communication Engineering

```text
Bachelor of Technology in Electronics and Communication Engineering.
```

## Tech stack

- GitHub
- GitHub Actions
- NumPy
- Pandas
- Python
- C#
- MATLAB
- TensorFlow
- PyTorch
- scikit-learn
- TypeScript
- Docker
- SQL
- LangChain
- Weights & Biases
- LangGraph
- Matplotlib
- AWS
- Azure
- Prompt Engineering

To contact Prachi, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Aastha Khatgarh](https://himalayas.app/@aasthakhatgarh): Data Analytics & Machine Learning Fellow Trainee, ElevateMe Bootcamp
- [Anurag Kumar](https://himalayas.app/@anuragkumar1): Senior Machine Learning Engineer, DashCloudAI
- [Justin Barry](https://himalayas.app/@justinbarry): ML Research Engineer, Independent
- [Utkarsh Dwivedi](https://himalayas.app/@utkarshdwivedi1): AI Research Scientist, Stealth Startup
- [Harshita Mandalika](https://himalayas.app/@harshitamandalika): Graduate Assistant, Texas A&M University
- [Affan Bin Usman](https://himalayas.app/@affanbinusman): Machine Learning Engineer, Gatik AI
- [Dustin Briscoe](https://himalayas.app/@dustinbriscoe): Lead AI Engineer, Cogentic Labs Inc.
- [Michael Williams](https://himalayas.app/@michaelwilliams4): Senior Machine Learning Engineer, ElevenLabs
- [Anthony Chen](https://himalayas.app/@anthonychen): Senior Machine Learning Engineer, Google
- [Yuxiang Xie](https://himalayas.app/@yuxiangxie): Staff AI/ML Engineer, OpenAI
