AI & Agentic Systems Engineering

AI & Agentic Systems Engineering

• Architect and deliver enterprise-grade AI solutions using Generative AI, Large Language Models and agentic frameworks, including AI copilots, domain-specific assistants and multi-agent workflows. Apply tools such as LangGraph, LangChain, Semantic Kernel or equivalent frameworks where suitable.

• Design planning, orchestration, reviewer, evaluator and execution agents, with appropriate human-in-the-loop controls, safety mechanisms and monitoring.

• Translate prioritized business and investment challenges into scalable technical architectures and production-ready AI services.

Generative AI, RAG & AI Platform Engineering

• Develop LLM-powered applications using leading commercial and open-source models and platforms, such as Azure OpenAI, Google Vertex AI, Hugging Face or equivalent, applying prompt engineering, structured outputs, reasoning frameworks and autonomous workflows.

• Design retrieval-augmented generation solutions using semantic and hybrid search, embeddings, enterprise knowledge bases, metadata enrichment, reranking and retrieval-quality optimization. Use vector databases, PostgreSQL with pgvector, Azure AI Search or equivalent services where beneficial.

• Establish LLMOps capabilities covering prompt lifecycle management, model evaluation, observability, performance and cost monitoring, testing, validation and responsible AI controls. Apply tools such as MLflow, LangSmith, OpenTelemetry or equivalent platforms where appropriate.

Full-Stack, Data & Cloud Engineering

• Lead hands-on development of modern React and TypeScript front ends and Python- or Java-based back-end services, APIs and microservices, using frameworks such as FastAPI, Spring Boot or equivalent.

• Build reliable data and analytics solutions using BigQuery and PostgreSQL, supported by cloud-native, event-driven and distributed architectures.

• Embed engineering excellence through automated testing, CI/CD, infrastructure as code, containerization, observability, monitoring, logging and site reliability practices, using Git, GitHub or Azure DevOps, Docker, Kubernetes, Terraform and relevant testing frameworks.

Machine Learning & Financial Analytics

• Design predictive and analytical models, including classification, ranking, recommendation and forecasting solutions, using appropriate supervised and unsupervised learning methods and established Python ML libraries such as scikit-learn, PyTorch or equivalent.

• Apply feature engineering, model explainability and robust validation to deliver transparent, decision-relevant analytics, using tools such as SHAP or equivalent where appropriate.

• Bring practical understanding of asset management, investment products and performance and risk measures to the design of relevant solutions.

Technical Leadership & Collaboration

• Define technical strategy, architecture and reusable engineering patterns for AI-powered products and platforms, while guiding prototypes from proof of concept to enterprise deployment.

• Partner with product managers, business stakeholders, use case owners and control functions to align priorities, manage trade-offs and deliver measurable outcomes.

• Mentor engineers, strengthen engineering standards and communicate complex technical concepts clearly to technical and non-technical audiences.