Join our Digital Engineering team, focusing on delivering innovative AI-driven software solutions.
Collaborate with cross-functional teams to design, develop, and use the latest AI Models.
Work on cutting-edge projects that address complex business challenges.
Requirements
7+ years professional software development (Python and Typescript preferred) with production ML/AI experience
Demonstrated delivery of at least one generative-AI solution in production (chatbot, summariser, code assistant, etc.)
Deep familiarity with transformers and orchestration stacks such as LangChain v0.2+, LlamaIndex or Semantic Kernel
Practical experience deploying or fine-tuning models on Azure OpenAI / AI Foundry or AWS Bedrock / SageMaker
Hands-on with RAG patterns, vector databases and evaluation metrics (BLEU, ROUGE-L, GPTScore)
Cloud-native engineering skills: Docker, Kubernetes (AKS/EKS), infra-as-code and automated testing
Agent frameworks (AutoGen 0.2/0.4, CrewAI) and tool-using agents.
Multimodal model workflows (image-text with GPT-4o, Gpt4o real time API).
Experience with embedding models
Workspace automation using agentic frameworks
Advanced RAG variants – familiarity with LongRAG, Self-RAG, GraphRAG and the trade-offs between leading vector stores (Pinecone, Qdrant, FAISS, Azure AI Search)
Multimodal & streaming LLMs – delivering real-time GPT-4o or Gemini 2 Ultra use-cases (image to text or speech) and cross-modal embeddings.