# Systems Architect at Oxman

> Onsite · United States · Staff · Other · open. Source: https://alderhq.app/jobs/ashby%3Aoxman%3Aac3c9b96-3372-4ab2-bc82-a7e0454a20e5 (read 2026-11-22).

## Facts (observed)

- Company: [Oxman](https://alderhq.app/companies/oxman)
- Location text: NYC Office
- Where it can be done from (inferred): Onsite · United States (evidence: "Location: NYC Office")
- Posted: 2026-10-19 (34 days ago)
- First seen by alder: 2026-11-07 · last verified: 2026-11-15
- Reposted: 0 times · edited: 1 times
- Apply on the employer's site: https://jobs.ashbyhq.com/oxman/ac3c9b96-3372-4ab2-bc82-a7e0454a20e5

## Pay and sponsorship

- Posted pay: $163k–$207k per year (from the listing's pay field)
- Market band for similar posted roles (New York, n 622): p25 $140k, median $175k, p75 $212k

## Description (the employer's text)

### OXMAN

OXMAN is a nature-based research and design company based in Manhattan. We incubate ventures and technologies that reimagine the relationship between humanity and the natural world. Working across disciplines—from architecture and ecology to computation and materials science—we develop nature-centric solutions to critical environmental challenges.

### EDEN

Existing environmental tools are trapped between two limits: remote sensing observes what is already on the ground, while traditional simulations only evaluate fixed plans someone has already drawn. EDEN bridges both. We are building a generative ecosystem digital twin that works from target outcomes, such as carbon sequestration, stormwater retention, microclimate cooling and biodiversity, to discover the optimal earthworks, planting and management sequence that achieves them.

Operating at the interface of representation learning, physics-grounded world models and autonomous optimization, EDEN maps satellite and geospatial data into a shared language of species functional traits and physical site fields (topography, light, moisture, wind, thermal, soil). Coupled physical solvers and fast learned surrogates simulate how these ecosystems develop over multi-year horizons, while a hybrid decision engine, combining AI agents with mathematical optimization, searches over procedural graphs to discover interventions whose outcomes can be predicted and validated.

EDEN’s technical work spans three teams: one that builds the platform, one that develops and validates the scientific modules, and one that combines those modules into applications. Our core components and first applications work today as research prototypes. As we engineer them into one cohesive system that turns ecosystem restoration and design into an engineering discipline with predictable, verifiable outcomes, we are seeking a System Architect to own the technical architecture across all three teams.

### Role Overview

OXMAN is seeking a System Architect to join the EDEN team as its first System Architect, owning the technical architecture across EDEN’s platform, science and applications teams.

This role sits at the intersection of systems engineering, scientific computing and applied AI. The System Architect will design and build the system that composes EDEN’s models, runs closed-loop simulation and optimization at scale, makes sure their results can be trusted, and delivers them to users through a single interface. The role is hands-on: the System Architect builds the first versions of the critical pieces themselves and makes the foundational decisions that are expensive to change later.

Few systems have to combine geospatial representation learning, physical simulation, mathematical optimization and AI agents while also producing results that hold up in the physical world. When models of microclimate, hydrology and ecological succession are chained over multi-year horizons, small errors can compound, and naive optimizers will happily exploit flaws in a learned surrogate rather than find designs that work in the field. The ideal candidate cares as much about whether a system’s outputs can be trusted as whether it runs, and understands that the architecture, search harness and validation guardrails they design will decide whether EDEN can grow from one validated application to many.

### Key Responsibilities

Define the core abstractions: Establish the shared schema of traits, physical fields and world states that every module reads and writes, a common contract for operators and evaluators, and the representation of EDEN’s procedural graphs. These graphs are design processes our teams author from real projects, which AI agents adapt to new sites, the decision engine searches and users inspect; their control nodes hold the executable programs that agents write and optimizers tune.

Architect the search, optimization and agentic control loop: EDEN’s decision engine pairs AI agents that adapt graphs and write design programs with numerical optimizers. Design the harness that translates user intent into formal problem bounds, with guardrails that keep agent and optimizer output within expert-validated physical and ecological limits, while orchestrating parallel search, inner-loop tuning, evaluation budgets and diagnostic feedback.

---
Data: alder (https://alderhq.app). Cite https://alderhq.app/jobs/ashby%3Aoxman%3Aac3c9b96-3372-4ab2-bc82-a7e0454a20e5 and the date you read it. Observed facts come from the employer's own listing; location reach, level, family and skills are inferences.
