M
Metavia muse
Research Engineer - AI Safety Systems and Guardrails
New York, NY, US$184K - $257K/yrPosted 2w ago
ResearchMid LevelFull-time
About the Role
We are seeking an experienced Research Engineer to join the System Safety team within Product \& Applied Research org at Meta Superintelligence Labs. This role will focus on researching and developing advanced machine learning models, novel algorithms, and scalable systems that improve the safety of Meta's AI products, including Meta AI and conversational, multimodal, and agentic experiences.You will bring current AI safety research into practical product safeguards, with a primary focus on guardrails, policy\-adaptable risk detection, adversarial robustness, and safe agent behavior. This is a hands\-on technical leadership role with end\-to\-end ownership of a significant safety area—from setting research direction and developing methods through rigorous evaluation, cross\-team integration, and continuous improvement in production.
### **Research Engineer \- AI Safety Systems and Guardrails Responsibilities:**
* Research and develop state\-of\-the\-art machine learning models and novel algorithms for AI safety, with a primary focus on guardrails, risk detection, policy adherence, and adversarial robustness
* Design, prototype, and implement safety systems for language models, multimodal models, and AI agents, addressing harmful assistance, jailbreaks, prompt injection, unsafe tool use, and unauthorized information disclosure across individual interactions and complete agent tasks
* Set the technical direction and research roadmap for a significant system safety area, leading complex initiatives across research, alignment, evaluation, product, and infrastructure teams
* Architect and optimize reusable safety components and machine learning pipelines, combining learned detection with explicit runtime controls and delivering scalable, low\-latency safeguards for real\-world applications
* Develop high\-quality training data, synthetic and adversarial examples, and representative benign cases
* conduct rigorous experimentation, ablation studies, and independent held\-out evaluation to improve safety, generalization, and robustness
* Measure the effectiveness of safeguards within the fully deployed system, balancing risk reduction with false refusals, legitimate task completion, privacy, latency, cost, and reliability
* Collaborate closely with model researchers, product managers, engineers, and evaluation, security, and policy partners to translate product needs and safety requirements into validated, production\-ready solutions
* Monitor, maintain, and iterate on deployed safety models and systems, using approved data and privacy\-preserving workflows to identify emerging failure patterns, create regression tests, and drive lasting system or model improvements
* Stay at the forefront of research and industry trends in AI safety, LLMs, multimodal modeling, adversarial robustness, and agentic systems
* reproduce, critically evaluate, and extend promising methods for product deployment. Mentor engineers and researchers to influence architecture and research decisions, and communicate findings through technical documentation, internal presentations, and external publications where appropriate
### **Minimum Qualifications:**
* Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
* Proven track record of research in one or more of the following areas: AI safety, deep learning, adversarial robustness, language models, multimodal machine learning, or agentic AI, demonstrated through original or materially improved methods and rigorous experimental evidence
* 3\+ years of experience in deploying machine learning models and systems at scale in an industry setting
* Demonstrated up\-to\-date expertise in relevant machine learning research advancements, including the ability to reproduce, critically evaluate, and adapt emerging methods to real\-world systems
* Hands\-on programming experience in Python and deep\-learning frameworks such as PyTorch
### **Research Engineer \- AI Safety Systems and Guardrails Responsibilities:**
* Research and develop state\-of\-the\-art machine learning models and novel algorithms for AI safety, with a primary focus on guardrails, risk detection, policy adherence, and adversarial robustness
* Design, prototype, and implement safety systems for language models, multimodal models, and AI agents, addressing harmful assistance, jailbreaks, prompt injection, unsafe tool use, and unauthorized information disclosure across individual interactions and complete agent tasks
* Set the technical direction and research roadmap for a significant system safety area, leading complex initiatives across research, alignment, evaluation, product, and infrastructure teams
* Architect and optimize reusable safety components and machine learning pipelines, combining learned detection with explicit runtime controls and delivering scalable, low\-latency safeguards for real\-world applications
* Develop high\-quality training data, synthetic and adversarial examples, and representative benign cases
* conduct rigorous experimentation, ablation studies, and independent held\-out evaluation to improve safety, generalization, and robustness
* Measure the effectiveness of safeguards within the fully deployed system, balancing risk reduction with false refusals, legitimate task completion, privacy, latency, cost, and reliability
* Collaborate closely with model researchers, product managers, engineers, and evaluation, security, and policy partners to translate product needs and safety requirements into validated, production\-ready solutions
* Monitor, maintain, and iterate on deployed safety models and systems, using approved data and privacy\-preserving workflows to identify emerging failure patterns, create regression tests, and drive lasting system or model improvements
* Stay at the forefront of research and industry trends in AI safety, LLMs, multimodal modeling, adversarial robustness, and agentic systems
* reproduce, critically evaluate, and extend promising methods for product deployment. Mentor engineers and researchers to influence architecture and research decisions, and communicate findings through technical documentation, internal presentations, and external publications where appropriate
### **Minimum Qualifications:**
* Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
* Proven track record of research in one or more of the following areas: AI safety, deep learning, adversarial robustness, language models, multimodal machine learning, or agentic AI, demonstrated through original or materially improved methods and rigorous experimental evidence
* 3\+ years of experience in deploying machine learning models and systems at scale in an industry setting
* Demonstrated up\-to\-date expertise in relevant machine learning research advancements, including the ability to reproduce, critically evaluate, and adapt emerging methods to real\-world systems
* Hands\-on programming experience in Python and deep\-learning frameworks such as PyTorch
Similar Jobs
Meta• 1mo ago
Research Engineer, AI (University Grad) | Ingénieur de recherche en IA (diplômé universitaire)
Montreal, Quebec, CanadaFull-time
I
Isomorphic Labs• 1mo ago
Research Engineer (LLM Performance), London
London, England, UKFull-time
P
Paragon Alpha - Hedge Fund Talent Business• 3w ago
Machine Learning Research Engineer - Hedge Fund - Systematic FX
London Area, United KingdomFull-time
S
ScaleWave• 1mo ago
Machine Learning Engineer
Coimbatore, Tamil Nadu, IndiaFull-time