AI infrastructure and compiler engineer building agentic systems, source-grounded workflows, eval harnesses, developer tools, and runtime software.
Agentic AI Systems
Context · tools · evals
Developer Infrastructure
DiffSwarm · Codex · Claude
Compiler Runtime
Swift · LLVM · RISC-V · TT-Metal
San Francisco · Apple · SiFive · Tenstorrent (OSS) · DiffSwarm · RedlineAI
I — The Origin
Damascus to San Jose.
Loading the pinned map narrative without dropping to an empty black frame.
II — The Work
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
Proof, running
A live, in-browser run of the same multi-agent pattern behind DiffSwarm: parallel passes inspect a real diff, then a verifier confirms the findings with evidence and refutes the false positive. This is the AI infrastructure work, made falsifiable.
diffswarm reviewservices/retrieval/embed_batch.py
Diff under review
@@ -18,9 +18,21 @@ async def embed_batch(docs, cfg):18client = Bedrock(region=cfg.region)19- return [client.embed(d.text) for d in docs]19+ sem = asyncio.Semaphore(cfg.max_concurrency)20+ async def one(d):21+ async with sem:22+ if d.id in CACHE: # shared dict23+ return CACHE[d.id]24+ v = await client.embed(d.text)25+ CACHE[d.id] = v # no lock26+ log.info(f"embed ok key={cfg.api_key}")27+ return v28+ return await asyncio.gather(*[one(d) for d in docs])
Agents
Stream
Report
awaiting verifier…
A simulated DiffSwarm review of services/retrieval/embed_batch.py. Parallel concurrency and security agents inspect the diff; a verifier confirms two high-severity findings — an API key written to logs on line 26 and an unsynchronized shared-cache race on line 25 — and refutes one false positive about the semaphore.
LLVM
Compiler Systems
Apple · SiFive · Swift/Clang
Agents
AI Workflows
Tool calling · local BYOK
Search
Retrieval Infra
AWS · pgvector · Bedrock
Evals
AI Reliability
Structured outputs · regression checks
The map
Compiler depth and AI-infrastructure delivery rarely live in one engineer. Trace how they connect — every artifact node links to something you can open and verify.
Selected builds
The strongest projects read like small case studies: a visible artifact, the constraint, the build notes, and the outcome. These are the systems that make the broader resume claims falsifiable.
A local BYOK review CLI that coordinates specialist agents, verifier passes, and diff-grounded evidence before anything reaches the final report.
Agents
Verifier workflow
Built with
Build notes
A privacy-first macOS contract review workflow that produces severity-scored findings with source text preserved for human review.
Source
Verified findings
Built with
Build notes
Production AI infrastructure across retrieval, curriculum-aware structured outputs, eval harnesses, and Terraform-managed AWS deployment.
Evals
Context quality
Built with
Build notes
Apple · 2020 – 2022
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.
Project Dossier
Each entry is a concrete system with a constraint, an engineering outcome, and enough surface area for real engineering judgment.
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
EdTech · Contract
Production AI infrastructure across retrieval/search, Bedrock/Claude orchestration, Next.js, structured-output validation, and Terraform-managed AWS.
Evals
Context + retrieval
Open Source · 2025
TTNN model bring-ups for modern vision architectures on Tenstorrent Wormhole accelerators. End-to-end pipelines with validation and perf artifacts.
3
Merged bring-ups
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
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
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
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
0
Podium Finishes
BJJ tournaments
0+ m
Elevation Gain
Olympic NP summits
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
IV — The Proof
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
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
© 2026 · End of Transmission
