Prajwal HD

I build agentic systems and the infrastructure to run them safely in production.

AI engineer with three years of cloud and software engineering at Opslyft. I care more about how a system behaves under pressure than what it is built with.

Resume View projects Email

Now

Updated June 2026

Open to AI engineer and backend/full-stack roles with end-to-end ownership. California, remote, or hybrid.
Building emberd, a Firecracker-based sandbox runtime that runs AI-agent code inside isolated microVMs. Also maintaining QuackCode and Gitwise.
Reading: AI Systems Performance Engineering right now, and papers on AI agents.

Projects

emberd

Run untrusted AI-agent code safely on your own machine, fully isolated from the host.

GoMicoVMAI-InfraSandboxingAI Agents

QuackCode

Developer ToolsElectronGit

Run coding agents on your real repos on Linux, with safe isolation and full history.

Gitwise

CLIGitTypeScript

Name commits and branches in seconds, without leaking secrets to the model.

Multimodal Malware Detection

PythonMLSecurity

Peer-reviewed thesis on whether vision and fusion models are worth their cost for malware detection.

All projects

Featured work

Peer-reviewedMDPI Electronics · 2026

Re-Evaluating Android Malware Detection: Tabular Features, Vision Models, and Ensembles

Hosahalli Dayananda, P.; Chen, Z.

Compares tabular static features, vision-based byte-plot models, and ensemble strategies for Android malware classification. Evaluates where modality choice changes the detection surface and where ensembles actually pay for themselves.

Read paper