Senior AI Software Engineer

What we offer

• Work on real, production AI systems at scale — not just prototypes
• Be part of building a modern AI platform used across multiple business domains
• Collaborate with international teams in a high-impact engineering environment
• Influence architecture, tooling, and best practices from day one

Requirements

• 5+ years of experience in software engineering, AI engineering, or ML engineering
• Strong Python skills and experience building production-grade APIs and backend systems
• Hands-on experience with LLMs, embeddings, and agent-based architectures
• Experience with cloud platforms (AWS and/or Azure) and modern deployment patterns
• Solid understanding of CI/CD, testing, and infrastructure as code
• Experience with monitoring, logging, and system reliability in production environments
• Good understanding of performance, scalability, and cost trade-offs in AI systems
• Strong problem-solving skills and ability to work in a cross-functional environment
• Fluent English

➕ Nice to have

• Experience with frameworks like LangChain, LangGraph, or similar
• Familiarity with RAG, vector databases, or search systems
• Experience with Kubernetes, Terraform, or advanced cloud setups
• Exposure to tools like Langfuse, LangSmith, MLflow, or OpenTelemetry

Responsibilities

• Take AI use cases from prototype to fully productionized solutions, ensuring reliability, scalability, and security
• Design and build cloud-native APIs and microservices for AI applications using Python (e.g. FastAPI, gRPC)
• Develop and maintain agent-based systems, including tool integrations and orchestration workflows
• Build and optimize RAG pipelines and/or text-to-SQL solutions, focusing on performance, cost efficiency, and accuracy
• Implement CI/CD pipelines and automated testing for AI services
• Deploy and manage applications in AWS and/or Azure using modern cloud architecture patterns (containers, serverless, etc.)
• Ensure full observability of AI systems (logging, tracing, monitoring, cost tracking)
• Introduce and maintain evaluation frameworks, guardrails, and quality controls for AI outputs
• Collaborate closely with Data, ML, Product, and Engineering teams to deliver robust, end-to-end solutions
• Contribute to architecture decisions, best practices, and engineering standards across the team