Research Engineer, Safety
Decagon · Not provided by source
MeritLog read this listing from Decagon's Ashby job board and last checked it on September 10, 2026.
Source: the employer's Ashby job board. Open the original listing for current details.
Job details
- Work model
- Not provided by source
- Salary
- $200K - $400K
- Location
- San Francisco
- Company website
- decagon.ai
Hiring context
How this role compares at Decagon
Decagon has 140 live roles in MeritLog’s catalog across 13 job families, and 71 of them are in engineering. 128 of those listings publish a pay range, a disclosure rate of 91%.
This role's posted range of $200K - $400K sits above 69% of the 108 other Decagon roles quoted over the same currency and period.
Decagon concentrates this hiring in:
Counted across the job boards MeritLog tracks, at the time this page was served. Pay comparisons use only listings that publish a complete range in the same currency and period.
What the role asks for
What you'd do
- Research and build safeguards against prompt injection, unsafe tool use, sensitive-data disclosure, policy violations, and hallucinated commitments
- Build adversarial evaluations, simulations, red-team datasets, and regression suites informed by production failures
- Develop and deploy classifiers, judges, reward signals, post-training methods, and runtime safeguards for safer agent behavior
- Analyze production traces and incidents to identify root causes, test mitigations, and measure their impact
- Partner with Security, Product, Infrastructure, Legal, and customer-facing teams to turn enterprise requirements into scalable safeguards and rollout practices
What they're asking for
- 2+ years of experience in AI/ML engineering, research, or AI safetyExperience
- Hands-on experience evaluating, post-training, or deploying language models or agentic systemsSkill
- Experience with modern post-training techniques, such as reinforcement learning, preference optimization, distillation, model routing, and synthetic-data generationSkill
- Experience with adversarial testing, model red teaming, prompt injection, policy enforcement, privacy, or safe tool useSkill
- Fluency in Python and modern ML tooling, with strong experimental judgment and the engineering depth to ship production systemsSkill
- Comfort owning ambiguous, high-stakes technical problems and making clear risk and product tradeoffsSkill
- Experience building safeguards for high-stakes or regulated enterprise workflowsSkill
- Familiarity with human-in-the-loop review, incident response, or responsible rollout frameworks for ML systemsSkill
Parsed by MeritLog from the employer’s own posting. The full description follows below.
Job description
About Decagon Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experiences. Our technology enables industry-defining enterprises like Avis Budget Group, Block’s Cash App and Square, Chime, Oura Health, and Hunter Douglas to deploy AI agents that power personalized, deeply satisfying interactions across voice, chat, email, SMS, and every other channel. We’re building a future where customer experiences are being redefined from support tickets and hold music to faster resolutions, richer conversations, and deeper relationships. We’re proud to be backed by world-class investors who share that vision, including a16z, Accel, Bain Capital Ventures, Coatue, and Index Ventures, along with many others. We’re an in-office company, driven by a shared commitment to excellence and velocity. Our values - Just Get It Done, Invent What Customers Want, Winner’s Mindset, and The Polymath Principle - shape how we work and grow as a team. About the Team Read more about the research team's work here: https://decagon.ai/blog/introducing-decagon-labs The Research team develops the model and decision-making stack that powers Decagon’s conversational agents for enterprise support. We research, adapt, and implement state-of-the-art techniques in model training, prompting, orchestration, and evaluation in order to make our agents more accurate, robust, and efficient in real-world deployments. Our goal is to push the frontier of applied conversational AI: agents that reliably understand nuanced intent, track long context, and take the right actions under uncertainty. We measure success the way customers feel it: higher resolution rates, better user satisfaction, and consistent behavior at scale. About the Role As a Research Engineer focused on Safety, you’ll be responsible for making Decagon’s AI agents safe, reliable, and controllable, from evaluation through production. You’ll identify real-world failure modes and build the models, evaluations, and safeguards that prevent them. We’re looking for strong engineers who want to advance applied AI safety in production. People here own their work end-to-end, ship real improvements, and are trusted to make high-impact technical decisions. In this role, you will - Research and build safeguards against prompt injection, unsafe tool use, sensitive-data disclosure, policy violations, and hallucinated commitments - Build adversarial evaluations, simulations, red-team datasets, and regression suites informed by production failures - Develop and deploy classifiers, judges, reward signals, post-training methods, and runtime safeguards for safer agent behavior - Analyze production traces and incidents to identify root causes, test mitigations, and measure their impact - Partner with Security, Product, Infrastructure, Legal, and customer-facing teams to turn enterprise requirements into scalable safeguards and rollout practices Your background looks something like this - 2+ years of experience in AI/ML engineering, research, or AI safety - Hands-on experience evaluating, post-training, or deploying language models or agentic systems - Experience with modern post-training techniques, such as reinforcement learning, preference optimization, distillation, model routing, and synthetic-data generation - Experience with adversarial testing, model red teaming, prompt injection, policy enforcement, privacy, or safe tool use - Fluency in Python and modern ML tooling, with strong experimental judgment and the engineering depth to ship production systems - Comfort owning ambiguous, high-stakes technical problems and making clear risk and product tradeoffs Even better if you have - Experience building safeguards for high-stakes or regulated enterprise workflows - Familiarity with human-in-the-loop review, incident response, or responsible rollout frameworks for ML systems Compensation $200K – $400K + Offers Equity This range reflects the expected compensation for this role. Compensation within the range is determined based on experience, skills, and the scope of responsibilities, with flexibility for candidates who demonstrate exceptional impact. In addition to base salary, we offer competitive equity. Final compensation may vary based on location within the United States. Benefits We proudly offer the following benefits for our full-time employees: - Medical, Dental, and Vision benefits for you and your family - Life Insurance and Disability Benefits - Retirement Plan (e.g., 401K, pension) - Parental Leave - Fertility and family building benefits through Carrot - Monthly stipend to support your wellness, lifestyle, and work-life balance - Daily lunches and snacks in the office to keep you at your best - Take what you need vacation policy (subject to local requirements; UK employees receive 25 days of statutory leave) These benefits are described in more detail in Decagon’s policies, may vary by location, and can change at any time according to applicable compensation and benefits plans.