Senior/Staff Applied ML Engineer - AI/ML Evaluation & Simulation

We're building the next generation of AI evaluation systems - and we're looking for a hands-on engineer who can bridge ML, software, and product to make AI systems more measurable, testable, and trustworthy. We're part of the AI/ML Evaluation organization, seeking a Senior or Staff-level Applied ML Engineer with strong software engineering skills and a solid understanding of machine learning. In this hands-on role, you'll help design and build intelligent systems that simulate complex interactions (including agentic workflows powered by LLMs), develop tools for extracting structured insights, and create robust evaluation datasets. You'll also contribute to building scalable platforms for simulation and behavior analysis. This role sits at the intersection of ML, engineering, and product - ideal for someone passionate about bringing clarity and rigor to real-world AI performance.

Description

We're looking for a pragmatic engineer who thrives at the intersection of machine learning and software development - capable of building robust, scalable systems that support evaluation and development of advanced AI capabilities, including large language models and agentic behaviors. A successful candidate is comfortable navigating ML, systems, and product domains. You bring strong software engineering fundamentals, experience building and maintaining end-to-end pipelines, and a practical understanding of how to evaluate AI systems in real-world contexts. You're curious about how LLMs behave in interactive or agentic settings, thoughtful about evaluation design, and eager to build tools that improve visibility and trust in AI. Above all, you enjoy collaborating across disciplines and bringing structure to complex, evolving problems.

Responsibilities

• Design and implement systems that simulate user-like interactions and workflows,
• Build tools and infrastructure to generate, manage, and analyze evaluation data
• Develop scalable pipelines to extract structured insights from simulation outputs
• Collaborate with scientists and engineers to instrument and assess model
• performance
• Engineer reusable, testable components for experimentation and evaluation workflows
• Help define and operationalize success metrics aligned with product and research
• goals

• 8+ years of experience in software engineering, ML engineering, or applied ML roles
• Proficiency in Python or another modern programming language (e.g., Java, Go, Swift)
• Experience building and maintaining production-grade systems
• Solid understanding of machine learning concepts, especially LLMs and their
• applications
• Excellent communication and collaboration skills with cross-functional partners

• Experience working on AI evaluation systems, LLM-based simulations, or agentic AI
• frameworks
• Background in building tools for data analysis, model evaluation, or synthetic data
• generation
• Familiarity with metrics instrumentation and observability in ML systems
• Experience designing pipelines for AI/ML workflows
• Exposure to applied research, generative models, or real-time systems
• Understanding of how model quality connects to product outcomes and user
• experience