
Software Engineer- AI
Alice (Formerly ActiveFence) · Ramat Gan, Tel Aviv District, Israel
- On site
- Full-time
- $180,000 / year
- Ramat Gan, Tel Aviv District, Israel
Job highlights
- Build AI safety training environments.
- Own RL Gym platform end-to-end.
- Lead a small, autonomous team.
- Collaborate with leading AI labs.
- Shape next-generation AI models.
About the role
About the Role
Alice’s Innovation team builds adversarial RL environments that train the world’s most advanced AI models to be safer. Our customers are the leading frontier AI labs, who use these environments for post-training reinforcement learning and safety evaluation. This is the bleeding edge of AI safety technology: the environments you build will directly shape how next-generation models learn to resist adversarial attacks.We’re looking for a Principal Software Engineer to own the RL Gym platform end-to-end: from architecting multi-site web environments that simulate real-world attack surfaces, to optimizing our in-house orchestration harness (AgenticVerse) for high-performance delivery into customer training pipelines.This is a builder role. You’ll lead a small team (including a dedicated web environments engineer), operating with high autonomy, moving fast from concept to working prototype to production system. You’ll interact directly with customer engineering teams to understand their infrastructure constraints and deliver environments that meet their scale and reliability requirements.
Why this role
This is one of the few roles in the industry where your code directly influences how the next generation of AI models are trained. You’ll be at the center of advancing AI safety, building systems that the world’s top labs depend on to make their models more robust. The work is technically deep, the problem space is genuinely novel, and the field is moving faster than any team can keep up with alone. There’s no playbook. You’ll write it.
What you’ll do:
Platform & Performance
- Own and evolve AgenticVerse, our in-house orchestration harness that provisions and manages RL environments at scale. Focus on performance: low-latency provisioning, high concurrency, minimal overhead per environment instance
- Design and build isolated, reproducible web environments using Firecracker microVMs or Docker containers
- Architect multi-site scenarios (3-4 interconnected web applications per task) with rich interactions: drag-and-drop, file uploads, authentication flows, LLM-in-the-loop components
- Implement deterministic verifiers that evaluate agent behavior with zero ambiguity
Customer Delivery
- Work directly with engineering teams at leading AI labs to integrate RL Gym environments into their training and evaluation pipelines
- Translate customer specs into working environments, iterating rapidly on feedback
- Own the technical relationship: SLAs, API contracts, integration architecture
- Adapt environment delivery formats to customer infrastructure (real-time API calls vs. offline batch, managed vs. raw artifacts)
- Build customer-facing UIs when needed (dashboards, environment configuration portals, monitoring interfaces)
Rapid Prototyping
- Take ambiguous problem descriptions and produce working prototypes within days, not weeks
- Validate new environment types, interaction patterns, and verifier approaches quickly
- Build internal tooling that accelerates scenario authoring and testing
Must have
- 8+ years of software engineering experience, with a track record of building production systems from zero
- Deep expertise in infrastructure: Linux, containers (Docker), VMs (Firecracker or similar), networking, cloud platforms (AWS strongly preferred)
- Strong Python skills and comfort with async/concurrent systems
- Experience building platforms or developer tools (not just consuming them)
- Full-stack capability: backend services, infrastructure-as-code, APIs, and frontend development (React or similar) for customer-facing interfaces
- Demonstrated ability to work autonomously with minimal specification, making sound architectural decisions under ambiguity
- Comfort working directly with external customers and translating technical constraints into engineering solutions
- English fluency (written and verbal) for customer-facing communication
Nice to have
- Experience with reinforcement learning infrastructure, training pipelines, or evaluation frameworks
- Background in security, adversarial testing, or trust & safety systems
- Familiarity with browser automation, headless browsers, or web scraping at scale
- Experience with Kubernetes operators or custom schedulers
- Prior work in a 0-to-1 environment (startup, innovation lab, or R&D team building new products)
About Alice
Alice is a trust, safety, and security company built for the AI era. We safeguard the communicative technologies people use to create, collaborate, and interact—whether with each other or with machines.In a world where AI has fundamentally changed the nature of risk, Alice provides end-end coverage across the entire AI lifecycle. We support frontier model labs, enterprises, and UGC platforms with a comprehensive suite of solutions: from model hardening evaluations and pre-deployment red-teaming to runtime guardrails and ongoing drift detection.
Key skills/competency
- Principal Software Engineer
- AI Safety
- Reinforcement Learning
- Platform Engineering
- Infrastructure
- Python
- AWS
- Full-stack Development
- Customer Facing Roles
- Startup Environment
Skills & topics
- Software Engineer
- AI Safety
- Reinforcement Learning
- Platform Engineering
- Infrastructure
- Python
- AWS
- Full-stack Development
- Customer Success
- Startup
How to get hired
- Tailor your resume: Highlight 8+ years of experience, production systems, infrastructure expertise (Linux, Docker, AWS), and full-stack capabilities (Python, React).
- Showcase autonomy: Emphasize experience building platforms/developer tools and working with minimal specifications.
- Demonstrate customer focus: Detail your experience working directly with external customers and translating needs into solutions.
- Prepare for technical deep dives: Be ready to discuss your experience with concurrent systems, microVMs, and architectural decisions.
- Understand the mission: Research Alice's role in AI safety and how your skills can advance their goals.
Technical preparation
Behavioral questions
Frequently asked questions
- What is Alice (Formerly ActiveFence) looking for in a Principal Software Engineer AI Safety candidate?
- Alice is seeking a Principal Software Engineer with 8+ years of experience building production systems, deep infrastructure expertise (Linux, Docker, AWS), strong Python skills, full-stack capabilities, and a proven ability to work autonomously and directly with customers. Experience in AI safety, RL, or startup environments is a plus.
- What are the key responsibilities for the Principal Software Engineer AI Safety role at Alice?
- The Principal Software Engineer will own the RL Gym platform end-to-end, architecting and optimizing adversarial RL environments and the AgenticVerse orchestration harness. This includes designing web environments, managing customer integrations, and rapid prototyping of new AI safety solutions.
- What kind of technical challenges will a Principal Software Engineer AI Safety face at Alice?
- Challenges include architecting multi-site web environments, optimizing high-performance orchestration harnesses, ensuring low-latency and high concurrency, designing isolated microVM-based environments, and integrating complex LLM-in-the-loop components for AI model safety training.
- How does Alice contribute to AI safety, and what is the impact of this role?
- Alice safeguards communicative technologies in the AI era. This role directly influences how next-generation AI models are trained to be safer by building adversarial RL environments used by leading AI labs, advancing the field of AI safety.
- What is the work environment like at Alice for a Principal Software Engineer AI Safety?
- The role involves high autonomy, fast-paced development from concept to production, and direct interaction with customer engineering teams. You'll lead a small team and operate in a '0-to-1' environment where you'll help write the playbook.
- What specific technologies are important for the Principal Software Engineer AI Safety role at Alice?
- Key technologies include Python, async/concurrent systems, Linux, containers (Docker), VMs (Firecracker or similar), cloud platforms (AWS), and frontend development (React or similar). Experience with RL infrastructure or security systems is also valuable.
Similar roles
Open positions we recommend based on this role.