Meta-harness on Islo
Public proof-of-concept for iterative agent-harness improvement on forkable sandboxes.
The career story progresses through navigation, kernels, containers, physical and genomic systems, production ML, build infrastructure, and AI execution. Evidence labels distinguish public, inspectable artifacts from employer-specific production work.
Public proof-of-concept for iterative agent-harness improvement on forkable sandboxes.
Public proposal reporting fresh compile ~46s, restored-cache ~13s, hot-cache ~3s; full test path ~75s to ~43s with restored cache.
Airflow Summit 2026: agentic MapReduce, sandboxed execution, state, caching, and Airflow as an orchestration layer for autonomous software engineering.
Nordic APIs Summit 2026: isolation and security boundaries for agent-to-tool execution.
OSDay: tracing thousands of short-lived AI agent runs and the observability problems created by disposable execution.
A partition-function reduce for forkable sandboxes, connecting statistical-computation ideas with modern agent execution.
Three-part series on Bazel architecture, caching/remote execution, build supply-chain infrastructure, and adoption trade-offs.
Practical integration model for build acceleration beneath GitHub Actions.
A C-to-Rust port treated as an evidence problem: disposable microVMs, deterministic checks, repeated failure, and measured compute cost.
Analysis of the process boundary between Bazel/Kleaf and nested Kbuild compilation.
Production deep learning and global semantic understanding for road-junction perception, with emphasis on difficult and rare cases. Public evidence here covers the role and domain; internal metrics remain private.
AWS-published technical case study co-authored by Yossi Eliaz on a gene-editing prediction engine using EKS, SageMaker, EFS, RDS, iterative learning, and production cloud workflows.
3D genome architecture, Hi-C, physical biology, graph theory, and reproducible large-scale analysis pipelines.
Current work spans cancer transcriptomics, chemistry-informed machine learning, and AI execution infrastructure.
HIT course spanning modern software engineering, ML engineering, cloud, containers, APIs, security, data, assessment tooling, and GTM engineering. Public course artifacts include a 455-question / 34-module mastery platform and an automated student-project evaluator.
Algorithms in a Jerusalem engineering organization publicly documented as specializing in high-end GPS receivers, GPS anti-jam, navigation, and guidance systems.
Low-level Android/Linux-kernel work around Marvell PXA mobile platforms during the period in which Samsung Galaxy phones and tablets shipped on Marvell PXA SoCs.
Embedded and firmware engineering continuing the low-level systems thread.
A bridge from low-level systems to container isolation and cloud-native security.