---
title: 'Reinforcement Learning Infrastructure Engineer at Elorian'
canonical: 'https://feeny.ai/job/reinforcement-learning-infrastructure-engineer-elorian-palo-alto-kkdrj7xwx678'
type: 'job'
last_seen: '2026-09-11'
---

# Reinforcement Learning Infrastructure Engineer at Elorian

- **Company:** Elorian
- **Location:** Palo Alto, CA
- **Compensation:** $200k–$400k
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-07-22
- **Last confirmed live:** 2026-09-11
- **Apply:** https://jobs.ashbyhq.com/elorian-ai-inc/7fc67724-f805-4715-a157-fa00e050bf8d

## Job description

## About Us

We are a well-funded, early-stage AI lab focused on building the next generation of frontier multimodal AI models. Founded by former DeepMind researchers, including Andrew Dai, who was previously a leader on Gemini. Our team currently consists of 20 world-class scientists and engineers. We recently raised $55M in seed funding from Striker Ventures, Menlo Ventures, Altimeter Capital, and NVIDIA. We are tackling some of the hardest problems in artificial intelligence, and we are growing fast.

## The Role

We're looking for an infrastructure engineer to design and build the core systems behind how we train our models with reinforcement learning (RL). You'll own the training infrastructure end to end, from rollout and reward pipelines to orchestration, reliability, and observability. The work spans both the algorithmic side of RL and the systems reality of running distributed training at scale, and you'll partner closely with our research team to keep RL training fast, stable, and dependable for the multimodal, visual reasoning models at the center of our work.

## What You Will Do

- Design, build, and optimize the infrastructure that powers our large-scale RL and post-training workloads
- Improve the reliability, scalability, and throughput of distributed RL training pipelines
- Build actor-learner architectures and orchestrate environment rollouts at scale
- Develop monitoring and observability tools that ensure high uptime, debuggability, and reproducibility across RL systems
- Collaborate with researchers to translate algorithmic ideas into production-grade training pipelines
- Improve GPU utilization and training throughput across the cluster

## What We're Looking For

Minimum qualifications:

- 3+ years of distributed systems experience, including building or optimizing large-scale RL training pipelines (PPO, GRPO, or similar on-policy methods)
- Experience with actor-learner architectures and environment rollout orchestration at scale
- Strong Python skills, plus PyTorch or JAX
- Experience with async training infrastructure, replay buffers, or simulation-based environment frameworks
- Multi-node GPU orchestration experience (Ray, SLURM, or Kubernetes)
- A track record of improving training throughput and GPU utilization at scale
- Strong engineering skills; ability to contribute performant, maintainable code and debug in complex codebases

Preferred qualifications (strong candidates may have some, not all):

- Experience with multimodal or agentic RL environments
- Experience with RLHF or reward modeling pipelines
- A self-directed builder who moves quickly and works across teams in an early-stage setting

Logistics Location: This role is based on-site in Palo Alto, California. Compensation: Depending on background, skills, and experience, the expected annual base salary range for this position is $200,000 - $400,000 USD, plus equity and benefits. Visa sponsorship: We sponsor work visas. We can't promise every case will succeed, but for the right person we'll work through the process with you. Benefits: We offer health, dental, and vision benefits, unlimited PTO, paid parental leave, and relocation support as needed.

Elorian AI is an equal opportunity employer. We are committed to building a diverse team and inclusive environment.

## About Elorian

## Company Overview
- **One-liner**: Elorian is an early-stage AI research lab building frontier multimodal AI models with a native ability to reason visually, moving beyond text-dependent systems.
- **Entity Type**: Private (Seed/Series A; $55M raised)
- **Headquarters**: Palo Alto, California, United States
- **Founded**: 2025
- **Founders**: Andrew Dai (Co-founder & CEO), Seth Neel (Co-founder & Founding Researcher), Forrest Huang (Founding Researcher), and others

## Core Business
- Primary industry: Artificial Intelligence / Visual Reasoning Research
- Target customers: B2B, enterprises in robotics, medicine, science, architecture, automotive, satellite imagery, and defense
- Mission or purpose statement: Building systems that natively understand and reason through the visual medium the way humans do, enabling AI to move from simple perception to higher-level reasoning in the physical world.

## Products & Services
- **Frontier Multimodal AI Models**: A research product lab developing new architectures for multimodal reasoning. These models directly interact with and manipulate visual representations (structure, relationships, constraints) rather than translating images into text before reasoning. Potential applications span engineering design, robotics, medical diagnostics, weather monitoring, disaster response, and precision agriculture.

## Market Standing
- **Valuation/Market Cap**: Not disclosed
- **Key Metric**: Total Funding – $55 million
- **Notable Investors/Partners**: Striker Ventures, Menlo Ventures, Altimeter Capital, with participation from 49 Palms and other investors; advisor and investor Jeff Dean (Google DeepMind Chief Scientist).
- **Growth Signals**: Came out of stealth on April 9, 2026; monthly employee growth of +28.6% (8 employees as of July 2026); website traffic surged +421.6% month-over-month; high-profile founding team from Google DeepMind and Apple; active hiring (Founding Technical Recruiter/Head of Talent).

## Competitive Advantages
- **Unique Approach**: Models are trained to reason directly with visual representations, bypassing the fragile text-dependent two-step process used by current vision-language models. This enables understanding of spatial, structural, and relational complexity that text-only or text-translated systems cannot handle.
- **Founding Team**: Researchers who led breakthroughs in pretraining, data, and vision modeling at Google DeepMind and Apple (including contributions to Gemini). Small, focused team with deep domain expertise.
- **Backing**: $55M from top-tier investors and AI luminaries like Jeff Dean, signaling confidence in the research direction.

## Strategic Focus
- **Visual Reasoning as a Path to AGI**: Elorian believes that native visual reasoning is a critical step toward truly general AI. Current priorities include advancing new training techniques, scaling the team with world-class researchers and engineers, and applying their models to real-world problems in robotics, science, and industry.

## Why Work Here
- **Culture**: Early-stage research lab with a tight-knit team of world-class scientists and engineers. Emphasis on long-term research and pushing the boundaries of AI.
- **Work Policy**: Hybrid workspace – employees engage in a combination of remote and on-site work (Palo Alto office).
- **Perks & Highlights**: Opportunity to work on some of the hardest problems in AI, with direct impact on fundamental research. Strong backing from leading investors allows for significant compute and resources. High growth trajectory with potential for rapid career advancement.

## Sources
1. [elorian.ai](https://elorian.ai/)
2. [linkedin.com](https://www.linkedin.com/company/elorian-ai)
3. [bloomberg.com](https://www.bloomberg.com/news/articles/2026-04-09/ex-google-deepmind-researchers-debut-startup-called-elorian-focused-on-visual-ai)
4. [builtin.com](https://builtin.com/company/elorian-ai-inc)

## Other roles at Elorian

- [Inference Infrastructure Engineer, Serving](https://feeny.ai/job/inference-infrastructure-engineer-serving-elorian-palo-alto-ec4rcp2xrvr7) — Palo Alto, CA
- [Founding Technical Recruiter/Head of Talent](https://feeny.ai/job/founding-technical-recruiter-head-of-talent-elorian-palo-alto-5x11mg261se0) — Palo Alto, CA
- [Member of Technical Staff](https://feeny.ai/job/member-of-technical-staff-elorian-palo-alto-g0n7fpjn35q2) — Palo Alto, CA
- [General Interest](https://feeny.ai/job/general-interest-elorian-palo-alto-6w6gkx6aggb4) — Palo Alto, CA