Applied AI Engineer

Responsibilities

You will architect core AI reasoning systems and agentic workflows to perform complex regulatory, financial, and spatial analyses. Additionally, you will build multimodal intelligence pipelines and integrate rigorous validation frameworks into high-stakes workflows.

Requirements

The ideal candidate has experience shipping production-grade LLM systems and possesses deep expertise in agentic orchestration and Python development. You should be reliability-obsessed, comfortable working with unstructured data, and capable of thriving in a fast-moving, autonomous team environment.

Skills

• Python
• LLM
• Agentic orchestration
• Multi-step planning
• Tool-use loops
• Self-correction
• Full-stack development
• Observability
• Evaluation
• Geospatial data
• GIS
• Modal
• GPU-backed inference
• vLLM
• React
• TypeScript

Benefits

• Competitive market-based compensation
• Founding equity
• Fully remote work
• Regular in-person team time
• Flexible schedules
• Unlimited PTO

About this role

WHO WE ARE

Vor Systems is building software to help accelerate capital deployment & project
development for renewable energy. We help developers, asset owners, investors,
and other stakeholders make better decisions, move faster, and cut costs to
improve financial returns.

To reach our climate goals, the world needs to build at an unprecedented scale,
but too much time and capital are trapped in the manual "soft costs" that keep
renewable projects in limbo. We are eliminating this friction with AI-native
workflows that help developers deploy assets and capital faster, providing the
digital infrastructure necessary to modernize the grid and bring the physical
world into an age of abundance.

We are a pre-seed, Gigascale Capital-backed company with paying customers. We’re
a small, ambitious team bringing together deep experience in AI, software, and
energy. Victor [https://www.linkedin.com/in/victorshao], John
[https://www.linkedin.com/in/remotezygote], and Guillaume
[https://www.linkedin.com/in/guillaume-noziere] have proven track records in
founding companies (Cozy
[https://www.prnewswire.com/news-releases/costar-group-acquires-cozy-services-ltd-with-plans-to-integrate-its-innovative-renter-screening-and-rent-payments-solutions-into-apartmentscom-300747156.html],
Greenify [https://tomkat.stanford.edu/innovation-transfer/greenify]) and scaling
global platforms (DoorDash, Meta, Amazon).

Help us build the software that powers the global energy transition.

HOW WE WORK

We operate in a domain where correctness matters. Our customers trust us with
sensitive financial, legal, and infrastructure data, and “mostly right” is not
good enough.

Our AI systems combine probabilistic model outputs with deterministic software.
That means we spend a lot of time thinking about system boundaries, validation,
evaluation, and failure modes, not just model quality.

You will join our early AI team, working closely with the team on model strategy
& agentic systems, data architecture & foundational pipelines, and product
direction & execution.

WHAT YOU’LL WORK ON

You will architect the core AI reasoning system and agentic workflows that plan,
execute, and verify complex regulatory, financial, and spatial analyses.

You will build multimodal intelligence pipelines on Modal (OCR/VLMs) to uncover
critical information in messy sources like scanned leases, permits, and
engineering schematics.

You will integrate rigorous validation and evaluation frameworks into
high-stakes workflows where correctness and reliability are paramount.

You will own AI-powered features end to end, from models and backend workflows
to the interfaces customers use to review results and take action.

WHO YOU ARE

Ideally
* You have shipped production-grade LLM systems with deep experience in agentic
orchestration, including multi-step planning, tool-use loops, and
self-correction.
* You are a Python expert with full-stack product experience, comfortable
connecting AI workflows to APIs, databases, and user-facing interfaces.
* You enjoy turning messy, unstructured data (legal, financial, spatial, and
conversational) into structured, usable, and intuitive insights.
* You are reliability-obsessed and care deeply about observability, evaluation,
and understanding how non-deterministic systems fail in the real world.
* You communicate clearly and thrive as an autonomous owner within a small,
fast-moving founding team.

Bonus points
* Experience with geospatial data, GIS tools, or mapping libraries.
* Experience adapting or fine-tuning open-source vision or language models.
* Experience with document-heavy domains or high-stakes financial/legal data.
* Experience with Modal, GPU-backed inference, or serving infrastructure such
as vLLM.
* Experience building user-facing products with React and TypeScript.

WHAT WE OFFER

💰 Competitive market-based compensation with meaningful founding equity.
🏗️ The opportunity to shape the AI systems, architecture, and company culture
from day one.
🏠 Fully remote work with teammates across the US.
🤝 Regular in-person time with the team when it makes sense.
🔋 Flexible schedules and unlimited PTO with a two-week minimum and an emphasis
on sustainability (pun intended).

About Vor Systems

Software Development · 2-10 employees