Senior Perception Engineer, Mill Edge
Own the line-scan pipeline: DeepStream, Holoscan, TensorRT, camera synchronisation and sub-100 ms defect classification on Jetson-class hardware.
Careers
Work on software that moves several hundred tonnes of paper a day.
This is not a dashboard company. The code you write changes a nip load, a steam schedule and a chemistry dose on a machine running at 1,200 metres a minute — which is why we care so much about limits, logs and failing safe.
Live example: Grade change PM4 · 135 gsm kraftliner → 110 gsm testliner, no break, ≤14 min off-spec
Open roles
Where we need people
All roles involve time in a mill. If that is unappealing, this is not the right company. [ASPIRATIONAL — hiring subject to funding]
Control & Autonomy Engineer
Own the policy engine and the guarded-write path into DCS and QCS systems. Experience with OT networks and IEC 62443 strongly preferred.
Simulation Engineer, Digital Twin
GPU-accelerated drying, forming and web-dynamics simulation in Omniverse. Continuously correct the twin against real reel data.
ML Engineer, Time Series & Prognostics
Break-precursor models, wet-end chemistry response and equipment prognostics from QCS, DCS and inspection history.
Papermaking Process Scientist
A paper-maker or process engineer who wants to encode what they know. Own grade models, furnish behaviour and the twin's physics.
Deployment Engineer, Mills
Take a site from rack to bounded autonomy: connectors, tag mapping, shadow mode, crew training and the baseline reconciliation.
Product Engineer, Run Experience
Make the run record something a machine tender at 03:00 actually wants to read. Vanilla-fast, dense, honest interfaces.
Mill Partnerships Lead
Own design-partner relationships end to end, from the first historian extract to the signed baseline reconciliation.
How we work
Six things about working here
Stated plainly so you can self-select.
You will visit mills
Everyone, including platform engineers. You cannot design guardrails for a machine you have never stood next to at 3am.
Safety reviews are real
Any change to the write path goes through a documented review. This is slower than a normal startup and deliberately so.
Small team, wide scope
Expect to own a system rather than a ticket queue, and to talk directly to the process engineers who use it.
Written by default
Design documents before code on anything touching control. Asynchronous, so mill time zones work.
We mark our claims
Internally and externally, design targets are labelled as design targets. Nobody is rewarded for optimistic numbers.
Remote with intent
Remote-friendly with regular on-site work at partner mills and periodic team gatherings.
Run timeline
What you would be building
This run is the product. Every role on this page makes some part of it work.
run_8f21c4
PM4 · 6.8 m trim · 1,180 m/min
SUCCEEDED
-
01
ingest.grade_target
SUCCEEDED
0.8 s
Mill Orchestrator — Pulled the 110 gsm testliner spec, customer tolerances and the standing energy budget from mill MES; locked the target envelope for the run.
-
02
twin.simulate
SUCCEEDED
34 s
Mill Orchestrator — Simulated 48 candidate transition recipes on the as-run paper-machine twin — forming, press, dryer and calender — and ranked them on off-spec tonnes, break risk and steam.
-
03
stock.refine
SUCCEEDED
2 m 10 s
Pulp-and-Stock — Stepped refiner specific edge load 1.9 → 1.4 Ws/m and pushed freeness toward 412 CSF while consistency held at 3.4%.
-
04
wetend.dose
SUCCEEDED
1 m 26 s
Wetend-and-Chemistry — Retention aid trimmed to 214 g/t and sizing to 1.1 kg/t against live charge and turbidity; first-pass retention recovered to 78% inside 90 seconds.
-
05
form.headbox
SUCCEEDED
1 m 05 s
Form-and-Press — Re-cut the slice profile across 78 actuators and set jet-to-wire to 0.994 to hold formation index through the basis-weight ramp.
-
06
press.nip
SUCCEEDED
48 s
Form-and-Press — Nip load reduced 620 → 540 kN/m to protect the lighter web; post-press dryness landed at 47.1%.
-
07
dry.steam
SUCCEEDED
3 m 18 s
Dry-and-Coat — Re-phased the steam schedule across 6 dryer groups and rebalanced the hood; reel moisture converged to 7.4% ±0.19 2σ at 6.1% less steam than the standing recipe.
-
08
inspect.web
SUCCEEDED
continuous
Defect-and-Inspect — 18 line-scan cameras streaming; two edge-crack precursors detected at the drive side and cleared by a 40 kN/m nip trim before either propagated.
-
09
approve.human
APPROVAL
52 s
Mill Orchestrator — Speed ramp 1,180 → 1,245 m/min exceeded the site autonomy threshold. Held for the machine tender; approved by J. Okonkwo at 04:57:12.
-
10
reel.qualify
SUCCEEDED
1 m 31 s
Quality-and-Conformance — Reel R-24188 released: full genealogy written (furnish, chemistry, CD profiles, defect map, operator actions) and checked against grade spec.
Process
How hiring runs
Four steps, roughly three weeks, no take-home longer than four hours.
Intro call
30 minutes with a founder on what you have shipped and what you want to own next.
Technical deep dive
60–90 minutes on a system you built, in real detail. We will go deep on failure modes.
Practical exercise
A scoped, paid exercise close to real work — a tool definition, a perception pipeline question, or a process analysis.
Mill conversation
A conversation with a process engineer or machine tender. Both directions: they assess you, you assess whether this world interests you.
Reference and offer
Two references, then a written offer with equity terms explained in full.
First month
A mill visit in the first four weeks, whatever your role.
Benefits
What we offer
A short list, honestly scoped for a pre-launch company. [ASPIRATIONAL]
Compensation and support
- Meaningful equity with plain-language terms
- Competitive base benchmarked to your market, not ours
- Remote-friendly with travel to partner mills covered
- Hardware and edge-development kit provided
- Conference and standards-body participation supported
- Genuine flexibility around mill-shift travel recovery
Accelerated computing
Physical AI, at the machine
Paper moves at 1,200 metres a minute. Perception has to be local, deterministic and fast, so Pulpum runs GPU inference at the mill edge and keeps training, simulation and optimisation in the cloud or on-prem.
Edge perception
8–24 synchronised line-scan cameras per machine. Sub-100 ms defect classification, sub-250 ms break-risk updates. [ASPIRATIONAL design targets]
Model serving
Vision, time-series prognostics, grade embeddings and process reasoning behind one orchestrator, with deterministic rollback by model version.
Training
Defect vision, break precursors, wet-end response and drying models trained on reel genealogy, QCS histories and operator corrections.
Digital twin
GPU-accelerated CFD, drying and web-dynamics simulation of the as-run machine — 10–100 candidate recipes evaluated per grade change.
Synthetic data
Rare break, contamination, wrinkle and formation-upset variants generated and always validated against real mill events before promotion.
Optimisation
Grade-change sequencing, dryer energy allocation, machine-speed balancing and maintenance windows under production and energy constraints.
Autonomy
Four levels, set per agent and per tag
A mill does not go from manual to unattended in one step. Pulpum makes the level explicit, auditable and reversible at any time.
| Level | What the agent does | What the human does | Typical time to reach |
|---|---|---|---|
| L1 · Advisory | Recommends setpoints and explains why | Enters every change manually | Week 1 |
| L2 · Supervised | Proposes a write; it executes on approval | Approves each write in the HMI | Week 3–6 |
| L3 · Bounded | Writes inside tag, rate and magnitude limits | Approves ramps and grade releases | Month 2–4 |
| L4 · Unattended | Runs the envelope without prompting | Sets the envelope; reviews the shift record | Month 6+ [ASPIRATIONAL] |
From the control room
What machine tenders say
Autonomy earns trust one shift at a time. These are design-partner quotes from pilot deployments [ASPIRATIONAL].
"The first thing that convinced the crew wasn't the control — it was the log. You can scroll back and see exactly why it dropped the nip. Nobody argues with a timestamp."
Machine tender · PM4 · Nordkraft Mills
"We had two people who could do a clean 135-to-110 transition. One retired in March. The twin now does the sequencing and the second one supervises it."
Production manager · Aurora Board
"Break prediction was the wedge. Ninety seconds of warning is the difference between a nip trim and four hours of threading."
Process engineer · Ternvik Paper
Guardrails
An agent that can move a nip needs a leash
Pulpum writes to production equipment. Every capability is scoped, every write is policy-checked, and every action is written to an append-only audit log the mill owns.
- Bounded action space. Each agent can only write to an explicit tag allow-list, inside per-tag rate and magnitude limits.
- Policy engine before every write. Autonomy level, shift, grade, interlock state and operator presence are all evaluated before a setpoint moves.
- Human-in-the-loop gates. Anything above the site threshold — speed ramps, grade releases, safety-adjacent moves — waits for a named approver.
- Immutable audit log. Append-only, hash-chained, exportable, and retained on the mill's own storage.
- Hard fallback. Loss of the edge node, the network or the model returns control to the DCS's last known-good state within one scan cycle.
- Tenant and IP isolation. Furnish recipes, grade models and defect libraries never cross a customer boundary. On-prem deployment available.
Compliance posture
| Standard | Scope | Status |
|---|---|---|
| SOC 2 Type II | Cloud control plane | RUNNING In progress [ASPIRATIONAL] |
| ISO 27001 | Company-wide ISMS | QUEUED Planned [ASPIRATIONAL] |
| IEC 62443 | Mill-edge OT security | RUNNING Design-aligned |
| GDPR | Operator data | SUCCEEDED Compliant |
| ISO 9001 / FSC | Quality + chain of custody records | SUCCEEDED Supported |
FAQ
Straight answers
The questions mill managers and process engineers actually ask in the first meeting.
For process roles, yes. For engineering roles, no — but you need to be genuinely interested in learning the process, because you cannot build good guardrails for a system you do not understand.
Remote-friendly, with regular travel to partner mills. Every role visits a mill within the first month.
Pre-launch. Incorporation, funding and the first commercial deployments are in progress [ASPIRATIONAL]. We say this clearly to candidates rather than after an offer.
Meaningful, with terms explained in full before you decide — strike price, vesting, cliff, exercise window and what happens on an exit.
Case by case, depending on the role and jurisdiction. Raise it in the first call so nobody wastes time.
Write to us anyway with what you would want to own. Small teams reshape roles around strong people more often than job boards suggest.
Get started
Tell us what you want to own
Send a note about what you have built and which part of the mill you want to make autonomous.