This is a REMOTE position. We only accept candidates located in EU, Norway, UK, and Switzerland.

We are looking for a Senior Engineer who is passionate about building scalable, async-first backend systems and modern AI architectures. You’ll join a small, highly skilled remote team of engineers and transformation practitioners working at the forefront of enterprise AI. You’ll design and implement backend services, event-driven architectures, and multi-agent communication layers using modern Python, Pydantic, async frameworks, and cloud-native tools.

Required experience

Core LLM Engineering (2+ years)

• Designing and building production-grade LLM-powered applications
• Working with foundation models (OpenAI, Anthropic, open-source models)
• Implementing complex skill/tool based or multi agents pipelines
• Prompt engineering and optimization, and/or fine tuning and model training
• Managing context windows, token optimization, and cost efficiency

Advanced AI Product Development

• Building end-to-end AI features integrated into user-facing products
• Handling real-world challenges: latency, reliability, prompt injections, hallucination mitigation
• Implementing guardrails, content filtering, and safety measures
• Designing agentic systems and multi-step reasoning workflows
• Experience with function calling, tool use, and structured outputs

Evaluation & Testing Infrastructure

• Hands-on experience with evaluation frameworks (Braintrust, Langfuse, or similar)
• Designing and implementing eval suites for LLM outputs
• Building regression test benches for prompt and model changes
• Understanding of evaluation methodologies: human eval, model-graded eval, reference-based metrics

Observability & Production Operations

• Implementing tracing and logging for LLM pipelines (Langfuse, Braintrust, or similar)
• Monitoring model performance, latency, and cost in production
• Debugging complex multi-step AI workflows
• Setting up alerting for quality degradation and anomalies
• Managing prompt versioning and deployment pipelines

• Languages: Python (primary), TypeScript/JavaScript
• Eval Tools: Braintrust, Langfuse, custom evaluation frameworks
• Infrastructure: Cloud platforms (AWS/GCP/Azure), containerization, CI/CD

• Strong software engineering fundamentals beyond just AI/ML
• Data-driven approach to measuring and improving AI quality
• Ability to balance speed of iteration with production reliability
• Clear communication about AI capabilities and limitations
• Proactive about staying current with rapidly evolving LLM landscape

About EggAI

EggAI is an enterprise-focused generative AI company on a mission to help large organizations move AI solutions from prototyping into production. We specialize in building safe, reliable, and scalable AI systems that deliver real business impact.