AI Engineer

Join a cross‑functional squad improving academic rules at scale. You'll design and ship real LLM solutions end‑to‑end - no people management, just meaningful delivery. Work with modern tooling, vector databases, and cloud AI, with flexibility and extensions likely.

Responsibilities

• Design LLM/RAG architectures and make cost-latency-accuracy trade‑offs
• Build pipelines for data ingestion, chunking, embeddings, retrieval, and generation
• Implement evaluation, guardrails, and PII/security controls
• Deploy containerised solutions with monitoring and clear handover docs
• Streamline rule authoring and generate fair application summaries via AI

Must have

• Deliver production LLM systems using Python and orchestration (e.g., LangChain/LlamaIndex)
• Apply RAG with vector stores (e.g., pgvector, OpenSearch, Pinecone, FAISS)
• Use AWS/Azure AI services and CI/CD; work hands‑on with Docker/Terraform
• Implement security (KMS, VPC, private endpoints, OIDC)

Nice to have

• Fine‑tuning (LoRA/PEFT) and retrieval re‑ranking
• Databricks/MLOps and enterprise compliance experience