# Rochan Avlur

> Autonomy Engineer at Skydio

Location: San Francisco Bay Area, United States
Profile: https://flows.cv/rochan

My interests lie in core systems, MLSys, and performance engineering. I enjoy solving complex challenges that arise when building reliable systems with strict performance requirements wrt. latency & throughput.

Previously, I conducted fundamental and applied ML research in reinforcement learning, bayesian optimization, and computer vision to solve challenging problems in medical image diagnosis.

## Work Experience
### Autonomy Engineer @ Skydio
Jan 2024 – Present | San Mateo, California, United States
Device Platform

### Research Collaborator @ MD Anderson Cancer Center
Jan 2022 – Jan 2023 | Houston, Texas, United States
• Developed a few-shot topology-aware segmentation model for quantitative analysis of cellular and tissue morphology.
• Implemented Triton kernels for topology-preserving segmentation.

### Graduate Research Assistant @ The University of Texas at Austin
Jan 2021 – Jan 2023 | Austin, Texas, United States
• Developed RL algorithms to learn policies for maximizing information-theoretic measures at scale via submodular maximization.
• Developed multi-modal algorithms for MRI and clinical data to identify biomarkers for Type 1 diabetes.
• Implemented high-performance parallel RL environment executor with C++11 threadpool, pybind11 and thread-safe pre-fetching that is x40 faster than Python implementation for terabyte-scale giga-pixel image data set.

### Undergraduate Researcher @ Mahindra University
Jan 2020 – Jan 2021 | Hyderabad, Telangana, India
• Researched gradient-free optimization schemes based on differential evolution for distributed neural network training.
• Implemented highly scalable OpenMPI & CUDA optimized algorithms that achieved x350 speed up on multi-GPU systems.
• Developed static code analysis methods based on linear algebraic transforms on LLVM IR for symbolic execution.

### Research Intern @ The University of Texas at Austin
Jan 2020 – Jan 2020 | Austin, Texas, United States
• Worked on Hierarchical & Multi-Agent RL for sample-efficient multi-target classification in giga-pixel images.
• Augmented self-supervised semantic segmentation models with Bayesian predictions for heteroscedastic uncertainty quantification.

### Research Intern @ International Institute of Information Technology Bangalore
Jan 2019 – Jan 2019 | Bengaluru, Karnataka, India
• Developed language models for validating semantic context & exposition coherence for Gooru Labs.
• Developed topic-guided generative language model, topic2document, based on seq2seq learning for virtual learning resource synthesis.

### Software Engineer @ ShowUpHotels (Startup)
Jan 2018 – Jan 2018 | Bengaluru, Karnataka, India
• Developed an automated tagging service based on language embedding models (lda2vec, doc2vec & word2vec).
• Published tagging tools and API for predicting sentence context using topic modeling as an open-source package, sptm (+15k downloads).


## Education
### Master of Science - MS in Computer Science
The University of Texas at Austin

### Bachelor of Technology - BTech in Computer Science & Engineering
Mahindra University


## Contact & Social
- LinkedIn: https://linkedin.com/in/rochan-avlur
- Portfolio: https://rochan-a.github.io

---
Source: https://flows.cv/rochan
JSON Resume: https://flows.cv/rochan/resume.json
Last updated: 2026-04-11