Neurosymbolic AI Researcher — Safe Multimodal Reasoning
Posted Updated
Description
microTECH Global LTD seeks a passionate researcher to advance AI safety at the intersection of AI and Safety. The role emphasizes solving challenging problems, scaling breakthroughs to production, and building interpretable, robust systems.
You will work on multimodal data, knowledge grounding, and neural-symbolic methods while collaborating with diverse teams to turn theory into scalable tools.
Design architectures for AI detection systems handling multimodal data. Explore visual QA, reasoning, and grounding techniques. Develop interpretable, unbiased AI with alignment to human values. Implement RLHF/RLAIF/Constitutional AI for LLMs and multi-step reasoning. Reverse-engineer neural networks and apply explainability tools. Develop data attribution methods and robust benchmarks. Defend against jailbreaking, prompt injections, and adversarial exploits. Communicate insights to stakeholders and translate research to production. Ph.D. in Computer Science or related field required. Strong track record in Explainable AI and Safety. Experience with LLMs/VLMs, neural-symbolic AI, and graph reasoning.Skills
Sign in to read and join the discussion.