AI Engineer

About Rivach

Rivach is an AI-native technology company and innovation studio building intelligent products, software systems and applied AI solutions.

About the role

Rivach is looking for an AI Engineer to design and build production AI systems across our products and technology solutions. You will work across large language models, retrieval systems, agentic workflows, AI APIs and backend services, taking ideas from experimentation through deployment. This role is suited to someone who enjoys building, not just experimenting with models, and is comfortable working across AI, software engineering and product problems.

What you'll work on

• Design and build production applications using large language models and multimodal AI systems.
• Develop retrieval-augmented generation, agentic and tool-using AI workflows.
• Integrate model providers, APIs, vector databases and structured or unstructured enterprise data sources.
• Build backend services and APIs that support AI-powered products and workflows.
• Design evaluation, observability and testing approaches for AI applications.
• Prototype new AI capabilities quickly and turn successful experiments into reliable production systems.
• Work with product, engineering and business teams to translate real problems into practical AI solutions.

What we're looking for

• Strong Python and software engineering fundamentals.
• Experience building applications using modern large language model APIs or frameworks.
• Understanding of embeddings, retrieval, prompting, vector search and RAG architectures.
• Experience designing APIs and backend services.
• Familiarity with databases, cloud environments, containers and production deployments.
• Ability to independently investigate ambiguous technical problems and turn them into working systems.
• Clear written and verbal communication.

What would make you stand out

• Experience with frameworks such as LangChain, LangGraph, LlamaIndex or equivalent tooling.
• Experience evaluating, tracing or monitoring production LLM applications.
• Experience with speech, voice AI or multimodal systems.
• Experience deploying machine learning models or inference systems.
• Open-source contributions, technically substantial personal projects or evidence of building AI systems end to end.