Senior Software Engineer, GenAI Security product (Vulcan)

We are looking for a Senior Software Engineer to build the application layer and tooling ecosystem that powers our GenAI security capabilities.

In this role, you are primarily a builder of systems and applications. You will work closely with other Software Engineers to bridge the gap between AI Research and Engineering by turning experimental concepts into production-grade software. Your scope covers three critical pillars:

1. Core Application Development: Building the Vulcan Platform (Full Stack) and internal application logic.
2. AI Agent Engineering: "Programming" models via advanced Prompt Engineering and workflow orchestration.
3. Tooling & LLMOps: Creating the operational pipelines and infrastructure tooling that serve these applications.

You will not just integrate APIs; you will architect the surrounding software ecosystem that makes our GenAI Red Teaming systems scalable, reliable, and user-friendly.

Learn more about us 👉

• Vulcan product: https://vulcanlab.ai/
• Vulcan LinkedIn: https://www.linkedin.com/company/vulcanlab-ai/
• AIFT group: https://aift.io/

-

How to apply

It will help us process your applications faster through https://job-boards.greenhouse.io/aift/jobs/5744136004

*Please apply with English CV, thank you.

-

What you'll do

1. Core Application & Platform Development (Full Stack)

• Vulcan Platform: Partner with Product and Design to build intuitive frontend interfaces (React, Next.js) for dashboards, configuration consoles, and visualization tools.
• Backend Services & APIs: Develop and maintain the essential APIs (FastAPI/Python) and microservices that power the Vulcan platform.
• Internal Tooling Ecosystem: Build frontend and backend tools that accelerate internal teams (Project, ML/AI), including configuration panels, data visualization pipelines, and evaluation interfaces.
• Guardrails & Security Features: Implement backend services for AI guardrails (content moderation, prompt filtering) and automated adversarial testing pipelines.

2. GenAI Agent & Logic Engineering

• Prompt Engineering as Code: Treat prompts as software logic. Lead the design and implementation of AI Agent behaviors, optimizing responses through structured Prompt Engineering techniques.
• Agent Workflow Design: Orchestrate complex, multi-step LLM workflows where the "application logic" involves chaining model interactions effectively.
• Response Handling: Design robust parsing and validation mechanisms to ensure raw model outputs are converted into structured, usable application data.

3. Tooling & LLMOps Infrastructure

• Tooling Infrastructure: Build and maintain the underlying tools and services that support the AI lifecycle, ensuring seamless integration between development, testing, and production environments.
• LLMOps Pipelines: Establish pipelines for evaluation, deployment, and monitoring to ensure model reliability and consistent performance.
• Asynchronous Processing: Architect robust task execution systems using Message Queues (Celery, RabbitMQ) to handle long-running asynchronous AI inference tasks.
• Observability: Implement logging and tracing (e.g., Langfuse, MLflow) to track system health, latency, and costs within the application layer.

-

• Professional Experience
  • 3+ years of total software development experience with a focus on web applications and backend systems.
  • Experience working in a development team of 3+ engineers
  • Familiar with collaborative development practices such as code reviews, issue tracking, and team-based delivery

• Technical Mastery
  • Strong Full Stack Proficiency: Proficiency in Python (Backend) and TypeScript (Frontend), with the ability to switch contexts effectively.
  • System Design: Solid understanding of System Design principles, specifically in building scalable web applications and microservices.
  • Engineering Mindset: You treat AI/LLMs as a software component. You focus on reliability, testing, and maintainability of the code surrounding the model.

• Soft Skills & Mindset
  • Independent Execution: Excellent ability to plan, organize, and execute features from concept to production with minimal supervision.
  • Cross-Functional Collaboration: Superior communication skills to translate requirements between AI/ML Researchers and non-technical stakeholders (PMs).

Nice-to-haves

• Leadership Experience: Proven experience leading an engineering team or mentoring junior engineers.
• Async Architecture: Deep familiarity with Task Executors and Message Queues (Celery, RabbitMQ) for high-concurrency workloads.
• LLMOps Tools: Experienced in tools like Langfuse, MLflow, or similar observability and evaluation platforms.
• CI/CD: Experienced in designing and maintaining CI/CD pipelines (e.g., GitLab CI) for automated testing and deployment.

Experience with these tools is a plus, but we value strong engineering fundamentals and learning ability over specific tool experience.

Tech Stack

• Core: Python, TypeScript
• Web: FastAPI, React, Next.js
• AI/Data Ops: Celery, RabbitMQ, PostgreSQL, Redis, MLflow, Langfuse

-

• Phone interview: 1 hour meet with HR
• Technical Assignment: A take-home or online assessment focused on System Design & AI Integration.
• Onsite Interview (2-3 hours):
  • Meeting with the Engineering Teams & Hiring Managers to discuss architectural approaches and collaboration.
  • Technical deep-dive on AI and software engineering standards.
  • Catch up with HR.