AI Engineer - LLM Applications

Overview

We are looking for a curious AI Engineer to join our growing AI team. In this role you will design, build, andproductionise intelligent systems that sit at the heart of our fintech platform from autonomous AI agents that orchestrate multi-step financial workflows to LLM-powered applications that deliver personalised banking experiences. You will work alongside product managers and data scientists to take AI initiatives from proof-of concept to production

KEY RESPONSIBILITIES :

- Agentic Systems: Design and build production-grade AI agents using agentic frameworks (LangChain,LlamaIndex, AutoGen) capable of reasoning, tool use, and multi-step decision-making in fintech contexts.

- LLM Applications: Develop, fine-tune, and evaluate LLM-based applications including RAG pipelines,semantic search, summarisation, and conversational interfaces for banking products.

- Model Integration: Integrate OpenAI, Anthropic, and open-source models (HuggingFace) with robustprompt engineering, output validation, and fallback strategies.

- Vector & Retrieval: Architect and manage vector databases (Pinecone, etc) for knowledge retrieval,embedding storage, and low-latency semantic search.

- MLOps & Deployment: Package and deploy AI services as containerised microservices on AWS / GCP /Azure using Docker and Kubernetes; maintain CI/CD pipelines for model and agent updates

REQUIRED SKILLS & QUALIFICATIONS :

- 2 to 5 years of professional software engineering or Machine Learning experience with strong Python skills

- Proven experience building and deploying at least one AI / LLM-based system in production

- Solid understanding of REST APIs, async programming, and microservices architecture

- Hands-on experience with LangChain or LlamaIndex for building agentic and RAG pipelines

- Experience calling and managing OpenAI or Anthropic APIs prompt design, token budgeting, functioncalling, and structured outputs

- Familiarity with HuggingFace ecosystem: model cards, transformers library, PEFT / LoRA fine-tuning

- Working knowledge of vector databases

- Experience with streaming LLM responses (SSE / WebSocket) in real-time applications

- Experience deploying containerised services with Docker and Kubernetes

- Comfort working on AWS, GCP, or Azure

Work Location: In person