Remote, Freelance, full-time

About us

Pass App is building the future of consumer finance: an AI-powered crypto platform where making money is easier than ever before. Our mission is to unlock the financial value in crypto that is today too complex and out of reach for most people — and make it accessible to the masses.

We’re looking for a passionate AI Engineer to join our team. Someone who thrives at the intersection of machine learning, systems design, and product development. Someone who can experiment fast, deploy models to production, and help us push the boundaries of how AI transforms consumer finance.

Your mission

Your mission is to design, build, and deploy AI agents and supporting systems that bring intelligence into the Pass App experience. You’ll work on everything from integrating foundation models to building RAG pipelines and tool integrations — turning complex data and workflows into seamless, reliable, and delightful user experiences. You’ll collaborate closely with product and engineering to deliver impactful AI features while continuously leveling up your technical craft.

What you’ll be doing

• Agent architecture & development: Architect, design, and lead the development of robust, stateful, and scalable AI agents using modern agentic frameworks (e.g., LangChain, LlamaIndex), setting technical direction and best practices.

• Systems integration: Strategize and oversee the integration of AI agent solutions with existing enterprise systems, databases, and third-party APIs to create seamless, end-to-end workflows across the product, while identifying and mitigating architectural risks.

• Model evaluation & selection: Evaluate and select appropriate foundation models and services from third-party providers, analyzing their strengths, weaknesses, and cost-effectiveness for specific use cases.

• Lifecycle ownership: Own and drive the entire lifecycle of AI agent deployment — from concept to production and beyond — for large, ambiguous, or highly complex initiatives. Collaborate closely with cross-functional teams, including product leadership to understand strategic needs and deliver highly effective agent solutions.

• Optimization & reliability: Troubleshoot, debug, and optimize complex AI systems, ensuring exceptional performance, reliability, and scalability in production environments. Mentor other engineers in advanced problem-solving techniques.

• Evaluation frameworks: Define, establish, and continuously improve platforms and methodologies for evaluating AI agent performance, setting key metrics, driving iterative improvements across the organization, and influencing industry best practices.

• Knowledge sharing & documentation: Establish and enforce best practices for documenting development processes, architectural decisions, code, and research findings to ensure comprehensive knowledge sharing and maintainability across the team and wider engineering organization.

What we’re looking for

• Experience: 7+ years of experience in software engineering and 1–2+ years of hands-on experience building LLM-powered agents.

• Knowledge of crypto, DeFi, or financial systems: Familiarity with blockchain data, wallets, or financial workflows — and how AI can unlock new value in this domain.

• Builder mindset: You’re scrappy and fast-moving but also think in systems that compound over time. 
  
  Core technical competencies

• LLM system design: Strong experience architecting and building multi-step agents (e.g., LangChain, LlamaIndex), with solid understanding of prompt engineering, context management, and LLM behaviors such as hallucinations and temperature effects. Familiarity with reasoning patterns like Chain-of-Thought or ReAct.

• Tool & API integration: Skilled at integrating agents with external APIs, databases, and third-party services (e.g., OpenAI, Anthropic) in production environments, with attention to scalability and security.

• Retrieval-Augmented Generation (RAG): Experience implementing RAG pipelines with vector databases and chunking strategies, and optimizing for performance and accuracy.

• Integrate memory & state: Experience implementing retrieval, long-term memory, and state tracking into agent architectures to enable persistent, context-aware reasoning.

• Evaluation & monitoring: Ability to define practical evaluation metrics for LLM performance and implement monitoring solutions for latency, accuracy, and reliability in production systems

• Fine-tuning & adaptation: Experience fine-tuning foundation models for specialized tasks. Understanding of data preparation, evaluation metrics, and balancing cost-performance tradeoffs in customized model deployments.

• Safety & reliability: Working knowledge of guardrails, prompt injection defenses, and fallback strategies to ensure robust and safe agent behavior.

• Performance awareness: Familiar with strategies to optimize LLM usage — managing token budgets, reducing latency, and applying caching or smart model selection.

• Programming & tooling: Proficiency in TypeScript, with experience using LLM SDKs and deploying cloud-based applications.

Bonus superpowers

• Strong product sense: Ability to bridge technical depth with user needs, translating advanced AI capabilities into intuitive, impactful product experiences.

• 0→1 product building: Proven track record of taking AI ideas from concept to production in fast-moving startup environments.

How we work

We’re a remote-first team spread across the world. Working across time zones pushes us to communicate clearly, keep context open, and move quickly without unnecessary friction. Our working hours center around European time zones, with enough overlap to connect with US hours for collaboration. We trust people to take ownership, make decisions, and deliver outcomes, while staying aligned through a mix of real-time teamwork and async communication.

Our culture is grounded in a few values that shape how we show up every day: ownership, speed, clarity, craft, curiosity, and mission. We believe in acting like founders, shipping fast, keeping things simple, sweating the details, staying open to new ideas, and always remembering why we’re here — to unlock the value of crypto for everyone.

Perks & benefits

• Ownership: Meaningful token allocation so you share directly in the upside you’re helping create

• Vacation: 25 vacation days per year 

• Learning: Annual education budget to invest in your growth

• Flexibility: Flexible work schedule so you can balance life and work on your terms

• Retreats: Annual team retreats in amazing locations — not corporate offsites, but trips you’ll actually look forward to

Join us

You’ll be building at the frontier of AI, crypto, and consumer finance. That means no playbooks, no best practices, no old ways of doing things. You’ll own growth from the ground up and help define how millions of people interact with money and grow wealth.

If you want massive upside and the chance to help create a category that reshapes global finance, this is the place to be. Join us!

Apply for this position