About Clarity AI 🪴 Clarity AI is a global tech company founded in 2017 with a unique mission: bringing societal impact to markets. We leverage AI and machine learning technologies to provide top international investors, governments, companies, and consumers with the right data, methodologies, and tools to make more informed decisions. We are now a team of more than 300 highly passionate and curious individuals from all over the world, with offices in New York, Madrid, London, Paris, and Abu Dhabi. Together, we have established Clarity AI as a leading sustainability tech AI company backed by investors and strategic partners such as BlackRock, SoftBank, and Deutsche Börse , who believe in us and share our goals. We are dedicated to cultivating an exceptional workplace environment, and we take pride in our culture, defined by our commitment to being fact-based, diverse, transparent, meritocratic, and flexible. We have plans to continue growing our teams globally, so if you would like to join us on this rocket ship, keep reading! Your work will shape and guide the sustainable decisions of investors, companies and consumers worldwide. About The Role 💻 We are looking for a Senior GenAI Platform Staff Engineer who is an expert in the deployment and scaling of LLMs and Agentic systems . In this role, you will bridge the gap between machine learning experimentation and production at scale by building the robust, highly efficient platform that powers our AI initiatives. While our Data Science teams focus on developing and tuning state-of-the-art models, you will be the owner of the platform that enables them. You will define best practices, build automated pipelines, and ensure that our infrastructure can handle complex agentic workflows with high reliability and performance. This is a role for a visionary who stays ahead of the daily shifts in the AI landscape and can rapidly adapt our stack to leverage emerging trends. For more insight into the technologies used by the engineering team at Clarity AI, please explore our Tech Stack What You’ll Be Doing 🚀 As a Senior GenAI Platform Staff Engineer, you will be responsible for: GenAI Platform Engineering: Designing and developing the core platform that enables the efficient deployment, scaling, and management of LLMs and multi-agent systems. Infrastructure for Agents: Building specialized infrastructure to support long-running agentic workflows, including state management, tool-calling interfaces, and complex reasoning loops. High-Scale Productionization & Model Serving: Scaling inference for LLMs to handle global demand while optimizing for latency, throughput, and cost. Implement standard batch and online serving with controlled rollback. Build & Delivery : Establishing the "Golden Path" for model deployment through a self-service path to move code, data, and models to production safely and reproducibly , including automated evaluation frameworks, safety guardrails, and CI/CD/CT pipelines. Strategic Vision & Product Management: Continuously monitoring the AI ecosystem and proactively evolving our platform to maintain a competitive edge. This includes adopting best practices in Platform Product Management and driving the adoption of golden-path solutions . End-to-End Observability: Implementing deep observability for LLMs, tracking not just system health but providing unified visibility into health, impact, and root cause across data, ML, and GenAI (including model hallucinations, token usage, and RAG performance). Collaborative Foundation: Providing the tools and abstractions that allow Data Scientists and stakeholders to move from a "tuned model" to a "production service" with zero friction. Location 🌍 The role is based in Madrid/Spain ( Remote / Hybrid ). What You’ll Need 👀 LLM & Agent Expertise: Deep, hands-on experience deploying Large Language Models and complex agentic architectures at scale. GenAI Platform Specifics: Proven experience in implementing Prompt Lifecycle Management (versioning, testing, and deploying prompts as code), an LLM Abstraction Layer (provider-agnostic access), and systems for Cost & Usage Control (visibility and limits on GenAI spend per use case). Evaluation & Benchmarking Mastery: Expert-level experience building automated evaluation pipelines and frameworks (e.g., Ragas, DeepEval, G-Eval) and implementing LLM-as-a-judge patterns to validate model quality, grounding, and safety in CI/CD. Platform & MLOps Mindset: A proven track record of building platforms or shared infrastructure. Deep understanding of MLOps concepts like Model Registry (versioning, state management, and lineage) and Model Monitoring & Drift Detection . 3+ years of experience in MLOps or high-scale Software Engineering with a focus on AI production environments. Technical Stack Mastery: Expert-level Python and deep experience with container orchestration ( Kubernetes , Docker ) and cloud infrastructure (AWS/GCP). AI Tooling & Frameworks: Proficiency with orchestration libraries (e.g., LangChain, LlamaIndex, CrewAI), vector databases (e.g., Pinecone, Weaviate), and inference engines (e.g., vLLM, TGI). Agility & Adaptability: The ability to learn and implement new technologies in a field that changes weekly. You should be a "fast mover" who enjoys constant evolution. Software Excellence & Governance: Strong fundamentals in API design, microservices, and "GitOps" methodologies, including the implementation of automated security and compliance by default. English Proficiency: Excellent communication skills (minimum C1 level), with the ability to articulate technical vision to both engineers and leadership. What We Offer 🥁 Competitive compensation, both in terms of base salary as well as equity plans that enable to you to share in our success Flexibility in ways of working both in terms of your schedule as well as your location, whether you prefer to work from home, the office, or abroad with access to a global network of co-working spaces Generous paid time off schemes , including vacation, sabbatical, religious observance and compensation days Meaningful benefits including private healthcare coverage, fitness and wellness programs covered through Wellhub, working-from-home allowances to help you set up your home office and cover monthly expenses Professional development with annual training budget for conferences, courses, certifications and access to top market e-learning platforms Collaborative environment with multiple offices around the globe, regular team activities and events as well as employee-led resource groups More About Clarity AI ⭐ Clarity AI’s Founder and CEO, Rebeca Minguela , is a successful entrepreneur who has been recognised by prestigious institutions like the World Economic Forum as one of the most distinguished leaders under 40. The leadership team has an international presence and is composed of professionals from leading tech, consulting, and banking firms, entrepreneurs, PhDs from top research institutions, and MBA graduates from top business schools. Clarity AI has received several awards: The Forrester New Wave - ESG Ratings, Data, and Analytics - Leaders for 2022-2024 Investment Week - Best Sustainable Investment Research & Ratings Provider 2023 Fast Company - Most Innovative Companies 2023 European Commission | EU Seal of Excellence 2020 World Economic Forum - Technology Pioneer 2020 World Economic Forum, Young Global Leader - Rebeca Minguela Clarity AI believes diversity, inclusion, and belonging are essential for creating an innovative and successful workplace. By actively promoting and engaging in sustainability efforts, we can help create a more equitable and resilient future for our planet and all its inhabitants.

• Own the multi-tenant platform. Architect and maintain the infrastructure that hosts hundreds of MCP codebases. Each isolated, each configurable, all observable from a single pane of glass (or MCP). • Build the data backbone. Design the pipelines that aggregate statistics, analytics, and performance metrics across every deployed instance. Make the data real-time, reliable, and actionable. • Ship the core app. Work hands-on in the main Waniwani application: a Next.js/TypeScript codebase with Drizzle ORM, React Query, and a modern component architecture. You'll build features that customers and internal teams use daily. • Design for scale. Make architectural decisions that hold at 10x. Multi-codebase deployment strategies, database partitioning, caching layers, job queues. Whatever the problem demands. • Automate everything. CI/CD pipelines, codebase provisioning, health monitoring, rollback systems. If a human has to do it twice, you build a system to do it forever. • Instrument relentlessly. Logging, tracing, alerting. When something breaks at 2am across 300 instances, the system should tell you exactly where and why, before anyone notices. • You'll work directly with the CTO. The architecture is yours to shape. The stack is TypeScript end-to-end.

• GenAI Platform Engineering: Designing and developing the core platform that enables the efficient deployment, scaling, and management of LLMs and multi-agent systems. • Infrastructure for Agents: Building specialized infrastructure to support long-running agentic workflows, including state management, tool-calling interfaces, and complex reasoning loops. • High-Scale Productionization & Model Serving: Scaling inference for LLMs to handle global demand while optimizing for latency, throughput, and cost. Implement standard batch and online serving with controlled rollback. • Build & Delivery: Establishing the "Golden Path" for model deployment through a self-service path to move code, data, and models to production safely and reproducibly, including automated evaluation frameworks, safety guardrails, and CI/CD/CT pipelines. • Strategic Vision & Product Management: Continuously monitoring the AI ecosystem and proactively evolving our platform to maintain a competitive edge. This includes adopting best practices in Platform Product Management and driving the adoption of golden-path solutions. • End-to-End Observability: Implementing deep observability for LLMs, tracking not just system health but providing unified visibility into health, impact, and root cause across data, ML, and GenAI (including model hallucinations, token usage, and RAG performance). • Collaborative Foundation: Providing the tools and abstractions that allow Data Scientists and stakeholders to move from a "tuned model" to a "production service" with zero friction.

Your job is to make Waniwani's infrastructure invisible at scale. We launched the first insurance app inside ChatGPT. Now hundreds of companies want to deploy their own AI-native storefronts through our platform. Every one of them needs its own MCP server, its own codebase, its own distribution. All running flawlessly, all interconnected, all managed by you. The Company Waniwani is building the AI distribution infrastructure for the $10T services economy. We enable companies to sell quote-based services (insurance, wealth, …) directly inside LLMs, where buying decisions are moving. Think Shopify, but for services. We're building the rails for AI-native commerce. This is Day 1 of a platform shift. Our ChatGPT insurance launch triggered $26B in market cap losses for the world's largest brokers in 48 hours. The press called it "the industry's ChatGPT moment." We call it Day 1. Why This Role Exists We're past proof of concept. The product works. Now we need to run it for hundreds of customers simultaneously, each with their own MCP server, their own data pipelines, their own distribution dashboards, without the platform breaking a sweat. This is a systems-level engineering problem. You'll own the architecture that lets Waniwani scale from dozens of deployments to thousands. Multi-tenant infrastructure. Multi-codebase orchestration. Real-time data flowing across hundreds of interconnected services. The kind of work where one bad abstraction costs you months, and one good one buys you years. We expect 95% of your code to be written by AI. Your value isn't in typing. It's in knowing what to build, how to architect it, and when the AI got it wrong. You'll operate at the speed of someone who treats LLMs as a core part of their engineering workflow, not a novelty. The bottleneck is judgment, not keystrokes. What You'll Actually Do Own the multi-tenant platform. Architect and maintain the infrastructure that hosts hundreds of MCP codebases. Each isolated, each configurable, all observable from a single pane of glass (or MCP). Build the data backbone. Design the pipelines that aggregate statistics, analytics, and performance metrics across every deployed instance. Make the data real-time, reliable, and actionable. Ship the core app. Work hands-on in the main Waniwani application: a Next.js/TypeScript codebase with Drizzle ORM, React Query, and a modern component architecture. You'll build features that customers and internal teams use daily. Design for scale. Make architectural decisions that hold at 10x. Multi-codebase deployment strategies, database partitioning, caching layers, job queues. Whatever the problem demands. Automate everything. CI/CD pipelines, codebase provisioning, health monitoring, rollback systems. If a human has to do it twice, you build a system to do it forever. Instrument relentlessly. Logging, tracing, alerting. When something breaks at 2am across 300 instances, the system should tell you exactly where and why, before anyone notices. You'll work directly with the CTO. The architecture is yours to shape. The stack is TypeScript end-to-end. This Role Is for You If You've built and operated systems at real scale. You've dealt with multi-tenant architectures where tenant isolation actually matters. You've managed codebases that couldn't fit in one repo and data that couldn't fit on one machine. You're a senior engineer with 5+ years of production TypeScript. You've been the person on-call when things break and the person who redesigns systems so they stop breaking. You think in systems, not features. When something works for one customer, you make it work for a thousand. Native or bilingual English required. French is a plus. Pluses Experience with multi-tenant SaaS platforms (tenant isolation, provisioning, billing) Built or operated big data pipelines (Kafka, ClickHouse, BigQuery, or similar) Deep PostgreSQL knowledge: partitioning, query optimization, connection pooling at scale Infrastructure-as-code experience (Terraform, Pulumi, or similar) Familiarity with MCP (Model Context Protocol) or LLM tool-use ecosystems Contributed to open-source infrastructure projects Experience with Next.js, Drizzle ORM, or similar modern TypeScript stacks Managed deployments across multiple cloud providers or edge networks Built internal developer platforms or deployment automation Why Waniwani Ruthless execution. Execution is what differentiates average outcomes and startup failure from massive impact. You will learn to execute surrounded by relentless doers and extremely ambitious teammates. Ownership. You'll architect the entire platform infrastructure from the ground up. Category creation. You won't join a market. You'll contribute to defining a category. Global. We sell global from day 0: US, Australia, Middle East, Korea… with offices in Paris, San Francisco, New York, and remote across Europe. Real equity. Meaningful ownership at the earliest stage. Best prep for founding. If you want to start your own VC-backed venture, this is the best battlefield to train on.