AI & Data . Full-time
AI Platform Engineer
Ship reliable LLM-backed features with evaluation loops, guardrails, and fallbacks for production traffic.
Role mission
You will own practical AI delivery from prompt and retrieval design to observability and quality assurance in live systems.
Responsibilities
- Design retrieval, evaluation, and fallback logic for LLM-powered workflows.
- Integrate AI services into existing product architectures with measurable performance targets.
- Create datasets and test harnesses for regression checks before release.
- Collaborate with engineering leads on cost-aware deployment strategies.
Core requirements
- Experience building backend services in Python or TypeScript.
- Practical understanding of prompt design, embeddings, and RAG patterns.
- Ability to design evaluation criteria for accuracy and reliability.
- Experience debugging production issues across APIs and data pipelines.
Bonus skills
- Hands-on with LangChain, LlamaIndex, or equivalent orchestration frameworks.
- Experience with model monitoring, drift detection, and quality dashboards.
- Background in information retrieval or applied NLP.
Apply for this role
Complete the form below. We review each application manually. Shortlisted candidates are usually contacted within five business days.