Member of Technical Staff - Safety

Sierra Ventures; San Francisco (CA); Sur place; USD 180 000 - 240 000; Plein temps

Avantages offerts par ce poste

Top-tier comp

Stock options

Healthcare coverage

Meals provided

Parental leave

Unlimited PTO

Visa sponsorship

Team events

Résumé du poste

Reflection is seeking a safety-focused AI researcher to own red-teaming and adversarial evaluation for our models. You will translate safety findings into concrete guardrails with the Alignment team and validate releases against risk thresholds.

Ideal candidates have MS/PhD or equivalent in AI safety, deep LLM safety expertise, and strong software engineering skills to build automated evaluation pipelines. RLHF/RLAIF experience is a plus, and you should thrive in a fast-paced startup.

Qualifications

• MS or PhD in Computer Science, ML, or related field, or equivalent practical AI safety experience.
• Deep technical understanding of LLM safety, adversarial attacks, red-teaming, and interpretability.
• Strong software engineering experience with automated evaluation pipelines or large-scale ML systems.
• Experience with RLHF/RLAIF and its impact on safety and alignment is a plus.
• Comfort in a fast-paced startup with high ownership and action bias.
• Willingness to make high-stakes decisions on model releases and safety thresholds.

Responsabilités

• Own the red-teaming and adversarial evaluation pipeline for Reflection’s models, probing for failure modes across security, misuse, and alignment gaps.
• Collaborate with Alignment team to translate safety findings into guardrails for reliable model deployment.
• Serve as gatekeeper for releases to ensure risk thresholds are met before shipping open weights.
• Develop scalable, automated safety benchmarks that adapt to evolving model capabilities.
• Research and implement state-of-the-art jailbreaks and defenses to stay ahead of vulnerabilities.

Connaissances

LLM safety

Adversarial evaluation

Software engineering

Python

RLHF/RLAIF

Formation

MS or PhD in CS/ML or equivalent

Outils

Python

TensorFlow/PyTorch

Description du poste

Our Mission

Reflection is a research lab making intelligence open and accessible for everyone to use, customize, and build on. We build open models that let anyone control their intelligence and help shape the future of AI. Our mission: make intelligence open and accessible to all.

About the Role

• Own the red-teaming and adversarial evaluation pipeline for Reflection’s models, continuously probing for failure modes across security, misuse, and alignment gaps.

• Work hand-in-hand with the Alignment team to translate safety findings into concrete guardrails, ensuring models behave reliably under stress and adhere to deployment policies.

• Validate that every release meets the lab’s risk thresholds before it ships, serving as a critical gatekeeper for our open weight releases.

• Develop scalable, automated safety benchmarks that evolve alongside our model capabilities, moving beyond static datasets to dynamic adversarial testing.

• Research and implement state-of-the‑art jailbreaking techniques and defenses to stay ahead of potential vulnerabilities in the wild.

About You

• Graduate degree (MS or PhD) in Computer Science, Machine Learning, or related discipline, or equivalent practical experience in AI Safety.

• Deep technical understanding of LLM safety, including adversarial attacks, red‑teaming methodologies, and interpretability.

• Strong software engineering capabilities with experience building automated evaluation pipelines or large‑scale ML systems.

• Experience with Reinforcement Learning (RLHF/RLAIF) and how it impacts model safety and alignment is a strong plus.

• Thrive in a fast‑paced, high‑agency startup environment with bias toward action.

• Willing to make high‑stakes decisions regarding model release and safety thresholds.

• Passionate about advancing the frontier of intelligence.

What We Offer:

We believe that to make intelligence open and accessible to all, you need to start at the foundation. Joining Reflection means building from the ground up as part of a talent‑dense team. You will help define our future as a company, and help define the future of open foundational models.

We want you to do the most impactful work of your career with the confidence that you and the people you care about most are supported.

• Top‑tier compensation: Salary and equity structured to recognize and retain our talent globally.

• Stock options: Everyone who joins and contributes to Reflection's success gets to share in the upside through stock options.

• Health & wellness: Comprehensive medical, dental, vision, and life, with an annual wellness allowance.

• Meals: Lunch and dinner are provided in the office daily.

• Life & family: 22 weeks paid parental leave for all new birthing and non‑birthing parents, including adoptive and surrogate journeys.

• Vacation days: Unlimited paid time off in the U.S. and 30 days in the U.K.

• Sponsorship support: We sponsor visas to help exceptional talent join our team and support long‑term immigration pathways where applicable.

• Team building: We have regular off‑sites, happy hours, and team celebrations.

Export Control Notice: This position may require access to technology or source code subject to the U.S. Export Administration Regulations. Any offer of employment for this role may be conditioned on the Company's ability to provide the candidate with access to such technology or source code in compliance with applicable U.S. export control laws, which may require the Company to seek government authorization.

Candidate and Employee Privacy Notice: We collect and process personal data about applicants for the purposes described in our Candidate and Employee Privacy Notice