LiveEO leverages satellite imagery and artificial intelligence to provide actionable insights that drive decision-making across various industries. For example, we detect trees and their height in high-resolution imagery to help protect power grids, identify dangerous construction work around critical infrastructure, and ensure compliance with deforestation regulations.

We are looking for a motivated AI Software Engineer to join LiveEO’s AI team. In this role you will contribute to the development of our geospatial AI solutions by building software solutions and tools that enable users to interact with geospatial data via Large Language Models.

You will work closely together with the ML Engineers in the team to integrate LLMs into agent frameworks and ensure smooth collaboration between training and reasoning systems. The ideal candidate has strong software engineering fundamentals and experience building agent systems around LLMs, translating research ideas into working implementations, designing evaluation setups to compare models and approaches, and developing the core Agent framework that ML Engineers can experiment with and extend.

• Build and maintain agent frameworks. Tool definitions and routing, planner or state graph, retries and timeouts, schema and format validation for structured outputs.
• Build, maintain and integrate RAG pipelines. Ingestion, parsing, chunking, embeddings, indexing, retrieval, reranking, context assembly, and grounding.
• Add lightweight observability. Structured logs, key metrics for latency, retrieval quality, and basic traces for end to end debugging.
• Evaluation automation: turn benchmark specs into repeatable pipelines with CI gates, scheduled runs, canaries, result dashboards, and trace/artifact linkage.
• Automate evaluation. Turn benchmark specs into repeatable jobs with CI, scheduled runs, canary checks, and a small results dashboard.
• Operate the synthetic data pipeline. Orchestrate jobs, control cost, deduplicate, cache, and log provenance.
• Prototype web app: deliver and maintain a simple chat/web console that integrates the agent; Chat with the agent, show logs, prompt and evidence, and allow toggling models or indexes.

• Excellent Python programming skills with a strong emphasis on writing clean, efficient, and maintainable code.
• Experience evaluating and benchmarking LLMs
• You have built RAG pieces before, such as Parsing and ingestion, embeddings, vector search, retrieval and reranking, context building.
• You have put together an agent style loop. Tool calling and routing, simple planners or state machines, with schema checks.
• Open mind, respectful attitude towards others and their work and good communication skills are a must.
• Understanding of geospatial data is a plus.
• Exposure to multimodal (text + vision) problems, including data handling, modeling, or end to end applications.

• The opportunity to create a product that can improve business processes and lives across the globe;
• Flexible working hours and hybrid work model - we trust our employees to get their work done while maintaining a healthy work-life balance;
• We empower employees to drive their own career development, take initiative and have the freedom to be creative and bold;
• Not an overtime culture - we take care that overtime is done only as a necessity and always offset with time off and rest;
• A collaborative and learning environment - frequent internal workshops, knowledge sharing sessions, journal clubs and hackathons;
• Office located in the centre of Berlin Kreuzberg with free fruit, nuts and drinks;
• Potential to participate in the employee stock option program;
• Urban Sports membership and BVG subsidy, corporate pension program;
• A diverse and vibrant international environment of 30+ different nationalities.

LiveEO is a well funded startup founded in 2018 and based in Berlin. Our primary service is modelling risk to our customers’ assets and infrastructure from vegetation, ground deformation and change detection. We currently have around 160 employees from all over the world with a variety of backgrounds