AI Safety Researcher

Job not on LinkedIn

4 days ago

Apply Now

Receive Emails with Similar Jobs

Machina

WebsiteLinkedInAll Job Openings

Aerospace • Hardware • B2B

Machina is a manufacturing engineering company that integrates next-generation technologies—casting, metal and sand additive manufacturing, and precision CNC machining—with computational design and process simulation to deliver sustainable, efficient serial and small-batch production. They specialize in aerospace- and automotive-grade aluminum castings, topology-optimized lightweighting, DfAM, post-processing (heat treatment, coatings), and end-to-end engineering services that turn AM prototypes into high-value production parts. Based in Istanbul, Machina focuses on industrial B2B collaborations to accelerate product development and reduce carbon footprint through optimized workflows.

1 - 10 employees

Founded 2021

🚀 Aerospace

🔧 Hardware

🤝 B2B

📋 Description

• Conduct research into AI safety, focusing on robustness, fairness, and interpretability of machine learning models used in build systems • Develop algorithms and frameworks that ensure the safe deployment of AI-powered automation in software build, testing, and CI/CD workflows • Work closely with engineering teams to integrate AI safety mechanisms and ensure robust error handling and fault tolerance • Investigate and mitigate risks associated with AI-driven decision-making in distributed build systems, especially in mission-critical operations • Contribute to the development of safety-critical AI models for optimizing performance, caching accuracy, and task coordination across various customer environments • Conduct studies on the ethical implications of AI in software development, ensuring that algorithms used in NativeLink align with responsible AI principles • Perform in-depth testing, model validation, and risk assessment to ensure AI systems meet reliability and safety standards • Collaborate with product managers and engineers to translate research findings into practical tools and features for our customers

🎯 Requirements

• 3+ years of experience in AI/ML research, with a focus on safety, robustness, and interpretability • Strong background in machine learning theory, with practical experience implementing models and algorithms • Expertise in AI safety frameworks, fault tolerance, and risk mitigation strategies for AI systems • Experience with reinforcement learning, adversarial training, and robustness testing of AI models • Proficiency in programming languages such as Python, C++, or Go, with hands-on experience in AI development libraries (e.g., TensorFlow, PyTorch) • Strong understanding of AI ethics, fairness, and the impact of machine learning algorithms in real-world applications • Ability to identify potential safety risks in AI-driven systems and design solutions to address them • Familiarity with distributed systems, cloud infrastructure, and build/test automation frameworks • Excellent problem-solving skills, with the ability to work independently and collaboratively in a fast-paced environment

🏖️ Benefits

• Competitive salary and benefits package • Opportunities for personal and professional development