Backend Engineer

About Atlys

Our mission is to enable every person on Earth to travel freely.

Travel should feel exciting. Instead, too much of it is still defined by paperwork, uncertainty, and processes that were never designed for travellers.

Atlys is changing that.

We're building an AI-first platform that removes friction and uncertainty from travel. To date, we've processed visas for 1M+ travellers across 127 countries. But we're still early.

The Role

We're looking for a Backend Engineer (AI) to build the systems that bring AI into production at Atlys, helping us make visa processing faster and simpler for travellers around the world.

This role is for someone with a strong backend foundation in Python who is excited by applied AI and LLMs, and who cares as much about reliability and scale as about shipping new features.

The Job

• Build AI-native backend services in Python that orchestrate LLMs, agents and tool calls across core product workflows.

• Build evals and reinforcement learning loops that measure model quality on real workflows, and use RL techniques (reward modelling, RLHF/RLAIF, RL fine-tuning) to continuously improve agent performance.

• Scale for volume and cost with async, event-driven workflows that handle peak demand while keeping latency and token spend in check.

• Own systems end to end from design to production, with strong testing, monitoring, observability and evals.

The Ideal Candidate

You'll likely thrive in this role if you:

• Have 4-7 years of backend engineering experience, including hands-on work building and running LLM-powered features in production.

• Are exceptionally strong in Python, including async Python, and have shipped production services with frameworks such as FastAPI, Django or Flask.

• Have hands-on experience with LLM APIs (OpenAI, Anthropic, Gemini) and the building blocks around them: prompt design, tool calling, structured outputs, RAG and vector databases (pgvector, Pinecone, Weaviate or similar).

• Know how to evaluate and harden AI systems, including eval datasets, LLM observability tools (Langfuse, LangSmith or similar) and trade-offs between accuracy, latency and cost.

• Have solid fundamentals in databases, distributed systems and cloud infrastructure, including PostgreSQL, Redis, message queues (Kafka, SQS or Celery), AWS or GCP, Docker and Kubernetes.