[Hiring] Staff AI Engineer @Yuno

Role Description

Yuno is looking for a Staff AI Engineer to be the senior technical leader for Payments Intelligence — the unit building the AI agents and intelligence products that make payments smarter across the platform. You'll architect and build production AI-agent systems like AIDA and NOVA, shape how Yuno applies LLMs and agentic AI to real payment problems, and raise the technical bar for the engineers around you.

This is a hands-on AI leadership role at the frontier. You'll design agents that hold real conversations with customers, recover revenue, automate operations, and surface intelligence to merchants — all in a production, multi-market, compliance-sensitive environment. Your impact comes as much from setting the technical direction for agentic AI as from the systems you build.

What This Unit Owns

• Yuno Agents (AIDA & NOVA)
  • AIDA, the agent that retrieves payment data and answers technical questions for support and operations teams
  • NOVA, the agents that recover revenue by turning failed payments into intelligent, multilingual customer conversations across channels
• AI Ops & Support — AI-driven automation that streamlines internal operations and customer support
• Client Intelligence — the AI and data products that surface insight and intelligence to Yuno's merchants

How AI Shows Up in This Role

• You're not adding AI to a product — you're building the AI that is the product: the agents, LLM pipelines, and intelligence systems at the core of Payments Intelligence
• AI is our default execution layer: you're expected to use AI-assisted tooling fluently in your own work, and to define how the unit designs, evaluates, and ships agentic systems responsibly

Your Contribution Will Be

• Agent architecture and technical leadership — own the architecture of Yuno's AI agents (AIDA, NOVA) and intelligence systems; set the technical direction for agentic AI and raise the bar for the team
• Production LLM and agentic systems — design multi-step agents with tool use, orchestration, memory, and retrieval-augmented generation (RAG), engineered for reliability and low latency at scale
• Conversational and multilingual experiences — build agents that hold real, dynamic customer conversations across channels (phone, WhatsApp) and 70+ languages, adapting to context and intent
• Evaluation, safety, and guardrails — define how the unit measures agent quality and safety, with rigorous evaluation, observability, and guardrails so agents behave reliably in a compliance-sensitive, multi-market environment
• Intelligence and data products — architect the client-intelligence systems that turn payment data into actionable insight for merchants
• AI Ops automation — build the AI-driven automation that streamlines internal operations and support
• Mentorship and cross-functional collaboration — mentor engineers and partner with Product, Data Science, and Staff Engineers across domains to ship complex, cross-team AI work

What Success Looks Like

Within your first 6–12 months, you've led the architecture of at least one core agent or intelligence capability, shipped agentic systems to production with real evaluation and guardrails behind them, and become the technical voice Yuno trusts on how to build AI agents responsibly at scale.

Qualifications

• Extensive software engineering experience, with a track record building and shipping production LLM or AI-agent systems
• Deep expertise in agentic systems — multi-step agents, tool use, orchestration, memory, and retrieval-augmented generation (RAG)
• Strong LLM application skills — prompt engineering, evaluation, and guardrails for reliable, safe outputs
• Strong Python for AI/ML, plus solid backend engineering (Go and/or Kotlin) to productionize systems at scale
• Model serving and LLM inference, with the cloud infrastructure to run AI workloads in production (AWS or similar)
• Evaluation and observability for AI — hands-on with tools like LangFuse, LangSmith, Braintrust, or MLflow — plus solid automated testing and CI/CD
• Proven technical leadership — mentoring engineers, driving technical vision, and delivering complex, cross-team projects
• English — advanced proficiency, written and spoken

Preferred Qualifications

• Fine-tuning, RLHF, or model customization
• Vector databases (Pinecone, Weaviate, or FAISS) and embedding retrieval
• Building agent workflows with MCP servers or modern agent frameworks
• Conversational AI and speech (speech-to-text / text-to-speech) and multilingual systems
• Experience in the payments or fintech industry

Nice to Have

• Running multi-tenant AI platforms or GPU/resource management at scale
• Data pipelines and orchestration (Airflow, Prefect) and warehouses like Databricks, Snowflake, or BigQuery
• Spanish proficiency

Tech Stack

• Languages — Python (AI/ML), Go and Kotlin (platform services)
• AI & LLMs — LLM APIs and open models, agent frameworks, MCP, RAG
• AI evaluation & observability — LangFuse, LangSmith, Braintrust, MLflow
• Data & retrieval — vector databases, feature stores
• Messaging — Apache Kafka, SQS
• Databases — PostgreSQL, Redis
• Infrastructure — AWS, Kubernetes, Docker, Terraform
• Observability — Datadog, OpenTelemetry
• CI/CD — GitHub Actions, ArgoCD
• Version Control — Git / GitHub

Benefits

• Competitive Compensation
• Remote Work — you can work from everywhere
• Home Office Bonus — a one-time allowance to set up your ideal home office
• Work Equipment
• Stock Options
• Health Plan wherever you are
• Flexible Days Off
• Language, Professional, and Personal Growth courses