We’re assembling a core engineering team to create AI systems that go beyond simple prompts—building agents capable of reasoning through multi-step tasks, using tools autonomously, and making reliable decisions under strict compliance requirements. This role is central to defining both the architecture and execution of intelligent systems that power identity verification and risk assessment at scale.
What You’ll Do
- Design and implement agent-based AI systems that can reason, plan, and use external tools effectively
- Develop production-grade workflows powered by large language models, ensuring consistency and safety
- Build evaluation frameworks to measure agent accuracy, reliability, and behavior over time
- Collaborate with product, risk, and compliance teams to turn high-level goals into functional systems
- Architect scalable, secure backend services that support autonomous AI operations
- Operationalize experimental concepts into robust, maintainable software
What We’re Looking For
- Proven experience building and shipping backend systems in production environments (6+ years)
- Strong proficiency in Python and modern frameworks like FastAPI
- Hands-on work with distributed systems, asynchronous processing, and workflow orchestration
- Direct experience building systems using agent architectures—such as tool-using agents or multi-agent coordination
- Experience implementing retrieval-augmented generation (RAG), multi-step reasoning pipelines, or agent orchestration platforms
- Familiarity with LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or OpenAI’s Assistants API
- Real-world deployment of LLM-powered applications beyond prototypes
- Deep understanding of system design, reliability, and operational constraints
Nice to Have
- Background in fraud detection, identity verification, risk analysis, or compliance systems
- Experience creating internal evaluation tooling for AI behavior and performance
- Knowledge of vector databases such as pgvector or Pinecone
- Experience working within regulated industries where safety and auditability are critical
Technology Environment
Our stack includes Python, Node.js (TypeScript), Golang, React, Kotlin, Swift, Dart, and Flutter for cross-platform reach. Infrastructure runs on AWS, orchestrated with Kubernetes and Terraform. We use PostgreSQL, RabbitMQ, and maintain ML models in Python. You’ll work across layers, shaping both infrastructure and intelligence layers of our systems.
Work & Culture
This role offers full flexibility to work remotely. We support relocations to Estonia or Spain with comprehensive assistance. You’ll join a team that values diverse perspectives, open dialogue, and technical rigor. We actively encourage applicants of all backgrounds and identities, especially those who may feel held back by imposter syndrome—we want your voice and your ideas.
Compensation includes stock options, generous vacation, additional recharge days, and a sabbatical after five years. Medical, dental, and vision coverage are provided, along with personal budgets for learning, health, and wellness.
