About your role

Develop and maintain agentic pipelines. Use tools including n8n, Python, JavaScript, Supabase, Pinecone, Huggingface and NotebookLM.

RAG & Knowledge Management Build vector databases, chunking/embedding strategies, guardrails, and evaluation strategies.

MLOps: Deploy AI models and maintain for reliability and speed. Implement knowledge base, evaluation pipelines, model versioning, and deployment workflows to production environments. Perform data collection, data sanitation, prompt engineering, context engineering, database optimization, token minimization.

Data Integration, Monitoring, and Reliability Integrate multiple data sources and services (e.g., CRM, support tools, product analytics, internal databases). Implement logging, error handling, and monitoring for automation workflows to ensure reliability and traceability. Test and debug flows, APIs, and scripts for production readiness.

Requirements

Solid computer science foundation and passion for machine learning. Degree qualifications are a bonus and not compulsory.
Strong proficiency in Python or JavaScript.
Strong ML fundamentals with hands-on experience.
Proven experience with LLMs: prompt design, function/tool calling, finetuning/ LoRA, RAG.
MLOps knowledge, artifact/version management, and automated evaluations.
Familiarity with cloud infrastructure (GCP, AWS)
Familiarity with agile software development (Scrum, Jira).
Good understanding of APIs and backend integration.
Experience with AI-assisted development tools (e.g. Claude workflows, AI code assistants) to enhance developer productivity is advantageous.