Omar Habra standing in the Glacier Meadows wilderness

Why this is rare

Large-company proof

Worked inside Apple compiler infrastructure across Swift and Clang.

Systems proof

Tuned RISC-V vector codegen and toolchain automation at SiFive.

AI product proof

Built agentic workflows, retrieval/search pipelines, tool-use systems, and eval harnesses.

Portfolio · 2026

OmarHabra

AI infrastructure and compiler engineer building agentic systems, source-grounded workflows, eval harnesses, developer tools, and runtime software.

Hiring Evidence Start a Conversation

Agentic AI Systems

Context · tools · evals

Developer Infrastructure

DiffSwarm · Codex · Claude

Compiler Runtime

Swift · LLVM · RISC-V · TT-Metal

San Francisco · Apple · SiFive · Tenstorrent · DiffSwarm · RedlineAI

Scroll

I — The Origin

Damascus to San Jose.

Loading the pinned map narrative without dropping to an empty black frame.

II — The Work

Hire for the slope, verify with the artifacts.

Swift/Clang compiler work at Apple. LLVM/RISC-V toolchains at SiFive. Production AI systems, agentic workflows, context engineering, evals, and open-source accelerator work after that.

Compiler infrastructure

Apple · SiFive

Agentic infrastructure

Context · tool calling · evals

Product tooling

Reliability · operator ergonomics

Manager read

Can work below the abstraction line: ABI, ASTs, codegen, ISA behavior.
Can work above it: product UX, tool-use systems, cloud reliability, customer constraints.
Can measure the result: benchmarks, eval harnesses, CI gates, production latency.

LLVM

Compiler Systems

Apple · SiFive · Swift/Clang

Agents

AI Workflows

Tool calling · local BYOK

Retrieval Infra

AWS · pgvector · Bedrock

Evals

AI Reliability

Structured outputs · regression checks

Apple · 2020 – 2022

Swift ↔ C++ Interop

ABI

Cross-language compiler work

Worked on Swift–C++ interoperability across the Swift/Clang toolchain: AST bridging, ABI integration, name mangling, and cross-language call support.

Implemented Swift/C++ interop changes across compiler boundaries
Supported Apple Silicon compiler work across ABI and backend issues
Built cross-architecture CI and log-triage tooling

SwiftClangASTABI

Project Dossier

Each entry is a concrete system with a constraint, an engineering outcome, and enough surface area for real engineering judgment.

RISC-V Vector Codegen

SiFive · 2022 – 2023

Tuned Clang/LLVM vectorization cost models and RVV codegen heuristics for RISC-V. Added microbenchmarks to catch compiler performance regressions.

RVV

Vector codegen

AI Tutoring Platform

EdTech · Contract

Production AI infrastructure across retrieval/search, Bedrock/Claude orchestration, Next.js, structured-output validation, and Terraform-managed AWS.

Evals

Context + retrieval

Tenstorrent TT-Metal

Open Source · 2025

TTNN model bring-ups for modern vision architectures on Tenstorrent Wormhole accelerators. End-to-end pipelines with validation and perf artifacts.

Merged bring-ups

RedlineAI

LegalTech · In progress

Privacy-first macOS AI workflow for contract review. Produces severity-scored findings with source-text evidence and human-reviewable outputs.

Source

Verified findings

DiffSwarm

DevTools · Agentic code review

Homebrew-installable multi-agent PR review CLI. Parallel AI agents inspect concurrency, security, and logic risks; verifier agents cross-check evidence.

Agents

Verifier workflow

GenAI Visual Processing

Retail · Contract

Latency and reliability work on a production GenAI image pipeline — intelligent caching, throughput tuning, and regression-catching evaluation.

Eval

Regression harness

III — The Athlete

Outside work, same operating system.

Marathons, Olympic-distance triathlons, BJJ podiums. The discipline is identical — train the system, log the telemetry, ship the result.

Field log · splits · open water · mat hours · 26.2 · 51.5 km · 3 podiums

0.0 mi

Marathon

Seattle · 2024

0.0 km

Olympic Triathlon

Swim · Bike · Run

Podium Finishes

BJJ tournaments

0+ m

Elevation Gain

Olympic NP summits

Omar at the Seattle Marathon finish line with friends

Seattle Marathon · 26.2 · Finish

Every mile, logged. Every finish, earned.

Training becomes measurable when every route, split, and effort gets turned into a field log.

Field Note

Finish lines are measurement, not mood.

The training log matters because it keeps the result honest: pace, distance, misses, repeat attempts, and the quiet accumulation underneath a public finish.

Race Telemetry

The route data stays in the chapter as supporting evidence: a quieter read on pace, terrain, and repetition after the finish-line image lands first.

Marathon · Olympic distance

Loading telemetry...

IV — The Proof

The camera roll, not the promise.

After telemetry comes the human record: race mornings, summit light, podiums, and finish-line proof.

Field archive

Observed, not art-directed.

Weather, fatigue, bad lighting, and the parts that feel too human to brand are what make the chapter credible.

BJJ Tour — Podium

Seattle · 2024

Open-Water Swim

Lake Tye · 1.5 km

Seattle Marathon

26.2 · 2024

Olympic Triathlon

Lake Tye · 2024

Seafair Triathlon

Seattle · 2024

After the Finish

Seattle · Field Record

V — The Signal

Build somethingdifficult.

Compiler work, AI infrastructure, product systems, public-sector modernization, or anything where correctness, performance, and judgment matter more than surface polish.

Omar Habra · 37.77°N · 122.42°W · San Francisco

Open channels

EmailDirect line LinkedInExternal link GitHubExternal link