About the Client
Our client is a global leader in pension asset management. They are currently driving a high-priority innovation project within their Risk Management Team.
They are looking for someone to join their team as an AI Engineer. It would be 6 months extendable contract with a chance converting to perm.
Key Responsibilities
- Collaborate with the Risk Management Team to design and build agentic AI systems utilizing multi-step tools, planning, and memory features.
- Implement robust RAG (Retrieval-Augmented Generation) pipelines, managing everything from data ingestion and chunking to advanced re-ranking and query rewriting.
- Build and maintain automated evaluation pipelines to benchmark model performance using frameworks such as RAGAS or LangSmith.
- Develop sophisticated prompt and system designs, including function-calling schemas, tool selection policies, and necessary safety guardrails.
- Oversee the deployment of specialized models, utilizing techniques like fine-tuning, distillation (LoRA/PEFT), and Mixture of Experts (MoE) architectures.
- Integrate retries and error-handling logic within AI workflows to ensure high reliability in a critical financial risk environment.
Requirements
- Bachelor's degree in Computer Science, Artificial Intelligence, Data Science, or a related quantitative field.
- 4+ years of experience in AI development, with a specific focus on deploying Large Language Model (LLM) applications.
- Proven expertise in Agentic frameworks such as LangGraph, AutoGen, CrewAI, or the OpenAI Assistants API.
- Hands-on experience with advanced RAG implementation and automated AI evaluation tools.
- Technical proficiency in Python and deep familiarity with model optimization techniques like LoRA and PEFT.
- Ability to work effectively in a high-stakes investment environment, translating complex risk requirements into technical AI solutions.
