> Markdown version of [/videos/1308-data-science-ml-ai-in-the-oil-and-gas-industry-at-ndt-global-dr-katja-traumner](https://www.wearedevelopers.com/videos/1308-data-science-ml-ai-in-the-oil-and-gas-industry-at-ndt-global-dr-katja-traumner). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Data Science, ML & AI in the Oil and Gas Industry at NDT Global - Dr. Katja Träumner

Dr. Katja Träumner argues deep domain knowledge now beats boilerplate coding. See how her team uses machine learning to prevent environmental disasters while rejecting toxic burnout culture.

- **Speakers:** Katja Träumner
- **Event:** 
- **Published:** March 12, 2025
- **Duration:** 32:32
- **URL:** https://www.wearedevelopers.com/videos/1308-data-science-ml-ai-in-the-oil-and-gas-industry-at-ndt-global-dr-katja-traumner

## Summary

Dr. Katja Träumner, Head of Data Science and AI at NDT Global, details how the oil and gas industry leverages machine learning to ensure pipeline safety. By analyzing vast datasets of ultrasound signals collected by diagnostic robots, algorithms detect corrosion and cracks at a sub-millimeter resolution. Rather than fully replacing human analysts, NDT Global employs a semi-automated pipeline where supervised machine learning filters massive datasets, "bringing the humans to the interesting pictures" for final validation. As AI increasingly handles boilerplate coding tasks, deep domain knowledge becomes the true differentiator for engineers. Träumner emphasizes that applying algorithms to specialized physical data requires expertise from diverse fields like physics and meteorology. This multidisciplinary approach makes niche data teams inherently more diverse and adaptable to complex, real-world constraints. Addressing the current state of women in tech, Träumner warns against backsliding diversity initiatives and champions visible leadership to break outdated structures. Sustainable engineering cultures reject the toxic "10x developer" myth and 70-hour workweeks, which inevitably cause burnout. Instead, companies must model true work-life balance, starting with leaders normalizing standard parental leave and flexible hours. Ultimately, developers seeking meaningful careers might find greater fulfillment in smaller enterprises where their software directly prevents environmental disasters, proving that "you are seeing immediately what you are doing" without needing to work for a massive tech giant.

**Keywords:** machine learning pipeline inspection, ultrasound anomaly detection, supervised learning models, oil and gas data science, semi-automated data analysis, domain knowledge in tech, women in technology leadership, dei initiatives in software, work-life balance in engineering, developer burnout prevention, niche tech company impact, multidisciplinary engineering teams, ai data filtering

## Chapters

1. **Inspecting oil pipelines with ultrasound technology** (00:01) — Using ultrasound technology to inspect high-pressure oil and gas pipelines for corrosion and cracks.
1. **Transitioning from academic physics to data science leadership** (02:20) — Shifting from a research physics background into leading and managing industrial data science teams.
1. **Applying supervised machine learning for practical rule extraction** (03:37) — Applying supervised machine learning to extract rules from massive labeled datasets rather than treating artificial intelligence as magic.
1. **Implementing semi-automated anomaly detection with human oversight** (06:14) — Keeping domain experts in the loop to review complex data anomalies flagged by machine learning models.
1. **Leveraging domain knowledge and diverse team backgrounds** (07:55) — Why specialized sector understanding and cross-disciplinary knowledge outweigh generic coding skills in complex technical domains.
1. **Pushing for female representation and leadership in technology** (11:09) — Breaking traditional organizational structures by actively filling tech roles with women to create role models and normalize diversity.
1. **Implementing company policies to support flexible work environments** (19:14) — Promoting flexible hours and equal parental leave as practical measures to build inclusive tech teams.
1. **Preventing developer burnout by avoiding toxic productivity trends** (23:31) — Recognizing the limits of extreme workloads and pushing back against unsustainable competition within software engineering teams.
1. **Finding direct product impact in specialized industrial companies** (27:41) — Working in smaller tech environments allows engineers to see the immediate real-world consequences of their software.
1. **Bringing diverse skills to industrial data science roles** (30:54) — Encouraging continuous learning and open-mindedness when applying for software and data positions in niche industrial sectors.

## Related Moments

- [Addressing developer burnout and the impact of artificial intelligence](https://www.wearedevelopers.com/videos/1504-cracking-the-code-to-tech-team-satisfaction) (from "Cracking the Code to Tech Team Satisfaction")
- [Career evolution in data engineering and AI platforms](https://www.wearedevelopers.com/videos/1209-coffee-with-developers-maria-apazoglou) (from "Coffee with Developers - Maria Apazoglou")
- [Navigating artificial intelligence adoption as a cultural transformation](https://www.wearedevelopers.com/videos/1627-pioneering-ai-assistants-in-banking) (from "Pioneering AI Assistants in Banking")
- [Building core AI literacy and algorithmic transparency](https://www.wearedevelopers.com/videos/1472-management-in-times-of-agentic-ai-the-human-premium) (from "Management in times of Agentic AI - The Human Premium")
- [Essential AI and human skills for future teams](https://www.wearedevelopers.com/videos/1623-breaking-silos-successful-collaboration-between-tech-business-teams-in-complex-enterprise-systems) (from "Breaking Silos: Successful Collaboration Between Tech & Business Teams in Complex Enterprise Systems")
- [Essential engineering roles in the generative AI space](https://www.wearedevelopers.com/videos/844-enter-the-brave-new-world-of-genai-with-vector-search) (from "Enter the Brave New World of GenAI with Vector Search")

## Related Articles

- [Women in Tech: Navigating Career Transitions and Breaking Barriers](https://www.wearedevelopers.com/magazine/491-women-in-tech-navigating-career-transitions-and-breaking-barriers)
- [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production)
- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)
- [MLOps – What’s the deal behind it?](https://www.wearedevelopers.com/magazine/125-mlops-what-s-the-deal-behind-it)

## Related Jobs

- [Lead Software Engineer - Data Engineering](https://www.wearedevelopers.com/jobs/ext/2000968-lead-software-engineer-data-engineering) at **Dynatrace**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**
- [Data Scientist](https://www.wearedevelopers.com/jobs/ext/1351648-data-scientist) at **Almedia**
- [Senior AI Agent Software Engineer (Go, Python) (m/f/x)](https://www.wearedevelopers.com/jobs/48277-senior-ai-agent-software-engineer-go-python-m-f-x) at **Dynatrace**
- [Senior Software Engineer, Data](https://www.wearedevelopers.com/jobs/48273-senior-software-engineer-data) at **Sportradar Media Services GmbH**
- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**