I build telemetry pipelines that turn noisy industrial signals into production evidence, and I operate LLM products end to end.Proof: 1y5m industrial fleet telemetry team work across a 700+ vehicle fleet, InfluxDB / Converter ownership, and untamedai.me planned, built, deployed, and operated solo.
Models open up. Data pipelines don’t.RT-2, GR00T, Cosmos, π0 — foundation models keep moving. What blocks the path to production is not the model but the data pipeline. And the people who have built data pipelines rarely overlap with the people who have run LLM products.
Three pillars proven on an industrial vehicle fleet. They port directly into robot manufacturing and traditional manufacturing.
Industrial vehicle fleet telemetry pipeline (700+ vehicles).A 4-tier distributed telemetry system delivered as part of a team for a 700+ vehicle production fleet. The data-processing modules listed below were my contribution.
[vehicle terminal] → Webhook → Bridge InfluxDB → V2InfluxConverterProcess (multi-process) → Measurement InfluxDB → Celery batch → Avro/GCS
Bridge InfluxDB was not a Kafka replacement; it acted as a time-series landing / replay layer for raw hex payloads so failed conversions could be reprocessed. The converter then normalized those payloads into measurement InfluxDB. The pipeline was designed and tested to absorb a 7,000 events/sec asynchronous event-stream load without becoming the bottleneck.
| Industrial vehicle fleet | Robot / manufacturing |
|---|---|
| 4-pack BMS async signals per vehicle | 30+ joints + F/T + vision per robot · N machines per line |
| CAN ISO-TP multi-frame | ROS2 chunked / OPC-UA chunked |
| Per-model .dbc / Excel DSL | Per-robot URDF / per-PLC vendor protocol |
untamedai.me — solo full-stack LLM product.untamedai.me — an AI companion that remembers users' emotions, planned, built, deployed, and operated end-to-end by one person.
What I want to build — robot-manufacturing and existing-manufacturing AI workflows.Current assets are industrial data pipelines and LLM product operations. Robotics, semiconductor, and steel domain depth are separated honestly as post-hire learning areas.
Teleop demos → automatic builds in RLDS / Parquet / MCAP training formats — the standards public corpora such as Open X-Embodiment ship in. Multi-source time alignment (vision · proprio · action · language) → quality filtering → segmentation → augmentation. Data quality at training time is the model’s ceiling; lifting that ceiling is the pipeline’s job. (deps: P1 + P2 + P3)target area
Reconciling simulator output vs real-robot telemetry on time, units, and distribution. Domain-randomization parameter distributions sourced from measured data automatically. Reality-gap metric dashboards. Sim-to-real failures are almost always alignment failures. (deps: P2)target area
Vision-Language-Action triplet sync, mining-ratio control across failure / success, automatic long-horizon segmentation. Splitting language instructions into semantic units + the cost / safety / iteration loop of LLM ops are exactly what untamedai.me handles daily. (deps: P2 + P3 + LLM product ops)partially transferred
Per-station measurements as a robot traverses the line + post-ship field telemetry, joined causally. End-of-line QC → field-failure traceability as one system. (deps: P2 + P3)designed, not built
A unified telemetry pipeline across multi-vendor PLC + OPC-UA + MTConnect for semiconductor / steel / cell / display lines. Production ops and model-training data on the same substrate. (deps: P1 + P2 + P3)
Machine-telemetry time-series → predicted end-of-line inspection results. Gradient-boosting baseline → Temporal Fusion Transformer / Patch-TST. Cycle-definition alignment in time is harder than the model itself. (deps: P2)
A natural-language interface for operators — “what caused the line-3 alarm at 02:00 last night?” style RAG over machine logs + SOP + history. Having owned this kind of LLM system end-to-end (§5 untamedai.me) ports directly into the line-assistant problem. (deps: P3 + LLM product ops)
Which machine on the line is the source of the defect? SHAP-based contribution decomposition, drift monitoring, training-distribution guards. (deps: P2 + P3)
The same primitives also work for fleet operations. The first priority is §6 (manufacturing + foundation data); these adjacent areas remain ready to deploy: a unified telemetry substrate across mixed fleets (humanoids / AMRs / cobots) · motor & joint predictive maintenance (RUL regression) · in-operation motion-anomaly detection (autoencoder / GMM). Primitive deps: P1 + P2 + P3 (same as §6).
One data substrate, nine AI outlets. People who have only handled the model don’t carry it to production. Only people who have handled the data pipeline and run an LLM product carry it all the way.
| AI workload | Primitive deps | LLM-ops leverage |
|---|---|---|
| Imitation-learning data build | P1 + P2 + P3 | — |
| Sim-to-real telemetry alignment | P2 | — |
| VLA triplet curation | P2 + P3 | ⭐ instruction segmentation |
| VLA data-quality LLM-as-judge eval | P3 + LLM ops | ⭐⭐ direct mapping |
| Cycle-level quality prediction | P2 | — |
| Time-series anomaly detection | P2 | — |
| Log → SOP matching (line-LLM precursor) | P3 + LLM ops | ⭐⭐ direct mapping |
| Instruction quality / safety eval | P3 + LLM ops | ⭐⭐ untamedai moderation direct |
| Operator LLM assistant (RAG over logs / SOP) | P3 + LLM ops | ⭐⭐ direct 1:1 mapping |
How I work — process signal. From running untamedai.me solo and from team work on industrial data systems, I have learned that how you work matters as much as the result. Three working postures.
Stack used on the industrial vehicle fleet, mapped to the equivalents that port into robot manufacturing and traditional manufacturing. Production code is under NDA.
| Ingestion / Bus | Industrial Fleet: Django · Flask webhook → Robot · Mfg: ROS2 · DDS · Kafka · OPC-UA · MQTT |
|---|---|
| Time-series store | Industrial Fleet: InfluxDB → Robot · Mfg: TimescaleDB · ClickHouse · MCAP |
| Metadata DB | Industrial Fleet: MySQL → Robot · Mfg: PostgreSQL |
| Distributed task | Industrial Fleet: Celery + django-celery-beat → Robot · Mfg: Celery · Airflow · Dagster · Ray |
| Single-node / distributed compute | Industrial Fleet: single-node multiprocessing → Robot · Mfg: Ray · Dask when distributed execution is required |
| Replay format | Industrial Fleet: Avro → Robot · Mfg: MCAP · Parquet · RLDS |
| Storage | Industrial Fleet: GCS → Robot · Mfg: S3 · Azure Blob |
| LLM stack (untamedai.me) | Next.js (frontend) · Python FastAPI (backend) · Supabase + PostgreSQL (DB) · Cloudflare (hosting) · Claude Opus + GPT 5.x (LLM) · Polar payments (flow built & validated, no transactions yet) → Foundation-model data / VLA / RAG |
Interviewing as of May 2026Woon · Aspiring Manufacturing AI Data Systems Engineer.Industrial vehicle-fleet telemetry pipeline as a team member → an LLM product (untamedai.me) operated solo: systems that turn raw telemetry into production evidence and product experience.