AI Engineer (GCP / RAG / Python)

Technologies we use

About the project

Your responsibilities

• Develop and deploy enterprise-grade GenAI applications: conversational search, RAG systems, multimodal agents, and domain-specific classification services.
• Build robust data and language-processing pipelines using Python, LangChain, and cloud-native components.
• Implement retrieval architectures using Vertex AI Search, Vector Search, or other vector database solutions.
• Optimize GenAI solutions for quality, reliability, latency, and cost - including RAG tuning and targeted fine-tuning where justified by business value
• Define and implement evaluation frameworks: automated tests, regression checks, hallucination/faithfulness indicators.
• Set up monitoring for model performance, app reliability, and business-aligned KPIs.
• Establish best practices around deployment, versioning, observability, incident reviews, and repeatable delivery patterns.
• Translate business goals into viable, scalable GenAI architectures on Google Cloud - with clear assumptions, risks, and acceptance criteria.
• Lead or co-lead discovery and feasibility workshops, focusing on use case framing and data readiness within the GCP ecosystem.
• Support presales: providing solution options, delivery approaches, and realistic implementation plans.

Our requirements

• 2-5+ years of hands-on AI/ML development experience, including LLMs and NLP.
• Strong Python engineering skills; practical experience with LangChain, Streamlit, and ML frameworks.
• Solid understanding of RAG architectures and LLM fine-tuning.
• Familiarity with the end-to-end AI/ML lifecycle, evaluation methods, efficiency metrics, and deployment patterns.
• Ability to communicate clearly with both technical and non-technical stakeholders
• Proficiency in English.

Optional

• Experience delivering AI solutions in consulting environments.
• Awareness of GenAI-related security considerations: PII, access control, prompt injection, data residency.
• Experience designing systematic evaluation frameworks for LLMs.
• Cloud-native deployment experience (containers, CI/CD, infra patterns) within GCP.

This is how we organize our work

This is how we work

This is how we work on a project

What we offer