Computational Ecologist

OXMAN•New York, NY

About The Position

OXMAN is a hybrid Design and R&D company that fuses design, technology, and biology to invent multi-scale products and environments. The fusion of disciplines within our work opens previously impossible opportunities within each domain—allowing design to inspire science and science to inspire design. At OXMAN, we question dominant modes of design that have divorced us from Nature by prioritizing humanity above all else (human-centric design). Although it is design that has caused this rift, we believe that design also offers the greatest opportunity to heal it. We propose a Nature-centric approach that delivers design solutions by, for, and with the natural world, while advancing humanity. In this pursuit, we reject all forms of segregation and instead call for a radical synergy between human-made and Nature-grown environments. This approach demands that we design across scales for systems-level impact. We consider every designed construct a whole system of heterogeneous and complex interrelations—not isolated objects—that are intrinsically connected to their environments. In doing so, we open ourselves up to moving beyond mere maintenance toward the advancement of Nature.

Requirements

A Ph.D. or equivalent experience in Computer Science, Computational Ecology, Systems Biology, or a related field.
Strong programming skills in languages such as Python, C++, or similar, with experience in frameworks like PyTorch, or JAX.
Strong foundation in modeling techniques (e.g., differential equations, agent-based modeling, network models, Bayesian approaches) for simulating ecological processes or population dynamics.
Experience handling large and often messy datasets common in ecology (e.g., climate data, remote sensing imagery, biodiversity records). Knowledge of spatial databases, parallel computing, or cloud-based data storage is a plus
Python (NumPy/SciPy/pandas), reproducible research workflows, and Git-based version control
High-performance model implementation (vectorization, profiling/optimization); familiarity with PyTorch or JAX
Ecological modeling methods: agent-based, ODE/PDE, network, and Bayesian/statistical modeling; uncertainty quantification
Geospatial analytics (GIS; GeoPandas/rasterio/GDAL) and spatial databases (e.g., PostGIS) for integrating environmental and biodiversity data
Remote sensing and gridded data handling (e.g., xarray; land cover/land use change; climate rasters); comfort with messy real-world datasets
Clear technical documentation (assumptions, data provenance, APIs) and maintainable code (testing, modular design)
Systems-level thinker who can translate ecological theory into tractable computational abstractions
Strong research judgment: literature synthesis, hypothesis framing, and disciplined model validation
Pragmatic engineer: prioritizes computational efficiency, robustness, and reproducibility over “toy” prototypes
Comfortable working with uncertainty, noisy data, and incomplete ground truth, typical of ecological problems
Clear communicator in interdisciplinary teams (design, biology, engineering); proactive stakeholder management
High ownership: independently drives milestones while aligning work to EDEN workflow integration needs

Responsibilities

Conceptualization and Research: Research and identify key ecosystem behaviours and interactions to create a comprehensive conceptual framework for general ecosystem modelling
Ecosystem Behaviour Modelling: Leading of the modelling of core ecosystem dynamics and interactions as defined in the conceptualization phase such as plant growth and succession etc.
Ecosystem Metrics Development: Development of quantitative metrics to assess ecosystem health, stability, and service provision.
Implementation and Documentation: Models will be implemented in a computationally efficient framework with thorough documentation to ensure usability and reproducibility.
Help in the gathering and integration of relevant environmental, ecological, and spatial data to underpin model parameters and validate model outcomes.
Conduct data analysis to in order to derive key insights necessary to develop ecosystem models and validate model parameters.
Technical documentation: Prepare comprehensive documentation outlining model assumptions, data sources, code structure, and operation for using and maintaining the models.
Continually communicate with the OXMAN team to ensure review of research, implementation, and seamless integration of the model into their workflows.
Participate in regular progress meetings (weekly or biweekly) with the team to review milestones, discuss challenges, and plan next steps.
Provide status updates summarizing progress, challenges encountered, and any adjustments to the project plan.