Senior Software Engineer, Applied AI (Remote from Poland)

At Oversee, we are reimagining how corporate travel is managed.

Our advanced technology and machine learning eliminate outdated, manual processes that hold companies back - driving cost savings , improving efficiency, and enabling smarter decision-making.

We combine travel analytics with actionable insights, giving global enterprises the tools to gain visibility into their travel spend while continuously optimizing their programs.

We are the global leader for air and hotel reshopping solutions and also provide “AgentSee”, an AI-powered productivity tool designed to help Travel Management Companies (TMCs) work smarter and faster. AgentSee automates manual tasks like processing traveler emails, booking flights, and managing travel arrangements; enabling TMCs to reduce costs and improve service quality.

If you are looking for a dynamic, fast-paced, and positive environment and want to help solve a $17B global problem - Oversee is the place to build, grow, and make an impact.

We’re growing fast, with exponential YoY revenue growth and partnerships with some of the world’s largest Fortune 500 companies.

Why join us?

You will join our AI team and help build production-grade AI agents used by global enterprises. You’ll work on real-world problems at the intersection of LLMs, automation, and large-scale travel data, with the freedom to shape both the technology and the product.

You’ll work on production AI systems, not demos. Think agent orchestration, retrieval systems, tool calling, workflow automation, large-scale integrations, and real-time decision-making.

Come shape the future of business travel with us!

What you’ll do:

• Design, build, and scale AI-driven systems that power our virtual agent capabilities, including conversational reasoning, retrieval, tool calling, and automation workflows;
• Develop backend services and data pipelines that integrate multiple APIs, including Amadeus, Sabre, internal systems, and third-party platforms, to support real-time decision-making;
• Build and deploy AI agents that solve real-world business problems;
• Design evaluation, testing, and observability systems to understand how agents behave in production and continuously improve their accuracy and reliability;
• Solve the engineering challenges that come with probabilistic AI systems, including latency, failures, model behavior, cost, and scalability;
• Own problems end-to-end, from understanding the problem and shaping the technical approach through implementation, deployment, and production monitoring;
• Own architecture decisions for distributed, high-performance AI applications;
• Help define engineering best practices and contribute to the technical direction of the team;
• Collaborate closely with Product and other teams to turn complex business problems into reliable AI-powered solutions.

About you:

• 5+ years of experience building production software systems;
• Strong Python and backend engineering skills;
• Strong experience designing and developing scalable, distributed applications;
• Hands-on experience building and shipping LLM-powered products or features to production;
• Experience with AI agents, agentic workflows, RAG, tool calling, or orchestration systems;
• Strong understanding of the challenges of production AI systems, including evaluation, reliability, latency, cost, and failure handling;
• Comfortable owning problems end-to-end and making technical decisions with a high degree of autonomy;
• Comfortable using modern AI coding tools as part of your day-to-day engineering workflow while maintaining strong ownership of code quality and technical decisions;
• Solid understanding of Linux runtime environments;
• Experience identifying and solving performance bottlenecks;
• Fluent English, written and spoken;
• Curious, proactive, and excited about learning new technologies;
• Comfortable operating in a fast-moving environment where requirements can evolve and engineers have significant ownership.

Bonus points if you have:

• Experience designing evaluation or monitoring systems for production LLM applications;
• Experience with embeddings, vector databases, and advanced retrieval architectures;
• Familiarity with frameworks and protocols such as LangChain, LangGraph, LlamaIndex, Google ADK, CrewAI, MCP, or similar;
• Experience experimenting with different models, retrieval approaches, or agent architectures;
• Exposure to travel-tech or GDS integrations, particularly Sabre, Amadeus, or Travelport;
• Hands-on experience with Kubernetes, AWS, Terraform, and CI/CD tooling;
• Open-source contributions, side projects, or technical writing

Our technology stack:

• Backend: Python, Django, Kotlin
• Frontend: TypeScript, React
• Infrastructure: Kubernetes, AWS, Terraform
• Data: High-scale pipelines & distributed systems

If you’re excited about building real AI products and not just talking about them, we’d love to meet you.

We are proud to be an equal …