MTS - Post-Training Lead

The posting, as Ironsite Ai wrote it

About Ironsite
The construction site is the most dynamic, unstructured physical environment in the world, and until now almost nothing that happens on one has been recorded. Ironsite records it. We design our own smart hard hats with cameras, deploy them with craft workers on the largest infrastructure projects in the country (data centers, LNG facilities, stadiums, hospitals), and turn each shift's footage into actionable insights superintendents read by 5 AM the next morning to improve the speed, efficiency, and predictability of their jobsite. We are pro-worker at our core, empowering the workforce that builds our country.

Our footage is now the world's largest dataset of first-person video from active construction sites, and we are using it to build a world model with the spatial intelligence to understand it. Our mission is to create general models that deeply understand dynamic, unstructured environments, predict how work will unfold, and use that understanding to supercharge human productivity and eventually enable robots to fill critical labor gaps. Our culture is one of radical transparency, intellectual honesty, low ego, rapid experimentation, and curiosity.

Ironsite is deployed across several of the top ten largest active construction projects in the country. We currently collect ~1,000 hours of new video every day from 8 states and expect to reach ~10,000 hours per day by the end of the year, all while maintaining a worker opt-out rate below two percent, enabled by a workforce-first architecture that anonymizes devices, captures no audio, and never releases raw video.

Ironsite is backed by leading investors (8VC, South Park Commons, Saga Ventures) and prominent operators across technology and construction, including Eric Schmidt, Jeff Dean, Jeff Rothschild, Mark Leslie, Scott Wu, Eric Glyman, Karim Atiyeh, Russell Kaplan, and others, alongside over a dozen construction industry operators who have joined us as partners in building this.

About the Role
As Post-Training Lead , you will report directly to the Chief Science Officer and own our post-training effort end to end: training, benchmarking, and deploying state-of-the-art VLMs that can interpret the complexity of a real-world construction site, built on data no other lab has. This is a hands-on technical lead role: train models, lead the researchers already working on SFT and RL, and help grow the team around this effort.

Open problems you could own in your first year

• Post-training for expert-level perception. Using SFT and RL (e.g., GRPO) to push VLM labeling of fine-grained construction activity beyond expert human taggers, across every trade.
• RLVR for agents that investigate the jobsite. Training agents with verifiable rewards to go beyond labeling and run their own research loop over a site's footage: form a hypothesis about what's slowing a crew down, dispatch a swarm to search thousands of hours of video for evidence, and return recommendations that field lea

[…]

• Deep expertise in fine-tuning and post-training large language or vision-language models (SFT, GRPO and other RL methods).
• Experience with technical leadership of other researchers, formally or informally, while continuing to do hands-on research.
• Hands-on experience with the challenges of video data, such as temporal reasoning, long-context modeling, and efficient processing.
• Experience optimizing inference, including quantization, distillation, sparsity, and efficient serving.
• Familiarity with MLOps tools for scalable model training and deployment.
• A strong interest in vision-language models and applying AI to real-world physical problems, including understanding the day-to-day lives of construction workers.

Why You'll Love Working at Ironsite

• Foundational Impact: Solve fundamental AI problems to transform one of the world's largest and least-digitized industries. Your models ship to real jobsites, not just papers.
• Ownership & Autonomy: We are a fast-paced startup where you'll have significant ownership over core research directions. We value intellectual curiosity, first-principles thinking, and iterating quickly to turn ambitious ideas into reality.
• Dream Dataset: Exclusive access to a massive, proprietary, and continuously growing corpus of egocentric jobsite video captured by real construction professionals doing real work on active jobsites. A moat that enables frontier research.
• World-Class Team: Collaborate with a small, elite team of experts who have a proven track record of building and shipping cutting-edge AI products.

Location & Compensation

• San Francisco Bay Area (on-site)
• Competitive salary and significant equity package
• Full benefits including health, dental, vision, and 401k +6% match
• Access to dedicated GPU compute resources for research and experimentation

The base salary range for this role is $250,000 – $400,000 per year.

Compensation
The base pay range for this role is $250,000 – $400,000 per year.