Lead Consultant(Development)

Technology, Data & Digital · Data, AI & Analytics · Data Science · Artificial Intelligence · Data Engineering

Smart Summary

AI-generated overview of this position

Seeking a Lead Consultant (Development) with expertise in AI/ML to engineer a Wealth Data Platform. Responsibilities include developing Text-to-SQL interfaces, designing ontologies, orchestrating autonomous agents, and integrating AI models within a regulated banking environment using Python, SQL, LLMs, and AWS.

Job Summary

Job Description: AI Lead Engineer (Wealth Data Platform)

Key Responsibilities

Key Responsibilities

Natural Language Democratisation: Develop and deploy Text-to-SQL and Text-to-Insight interfaces that allow non-technical Wealth Managers to interact with the conformed data layer using LLMs.
Ontology & Knowledge Graph Engineering: Design and implement a domain-specific Wealth Ontology. Graph databases (e.g., Neo4j or Snowflake Relational Graphs) need to be leveraged to map complex client relationships and financial hierarchies that standard SQL fails to capture.
Agentic Workflows: Build and orchestrate Autonomous Agents (using frameworks like LangGraph, ADK, CrewAI, or AutoGen) capable of executing multi-step financial reasoning such as automated portfolio rebalancing checks or proactive client insight generation.
Modern Data Alignment: Ensure all AI models are integrated into the SageMaker Unified Studio and adhere to the bank’s OBDQ standards to prevent "hallucinations" in regulated client reporting.
Productivity Tooling: Work with Analytics Engineers to embed LLM-based chatbots into front-line tools to reduce manual data gathering time for client-facing staff.

Skill Requirements

Technical Requirements

AI/ML Foundations: Deep expertise in LLM orchestration (RAG), Fine-tuning, and Prompt Engineering.
Graph Technology: Experience building Ontologies or using Graph-based RAG to improve the retrieval of structured/unstructured wealth data.
Data Stack: Proficiency in Python and SQL. Familiarity with Snowflake (Cortex), AWS SageMaker, and Kafka for real-time agent triggers.
Engineering Rigor: Experience with LLMOps (monitoring, evaluation, and versioning) within a highly regulated Banking (FCA/PRA) environment.
✅ Mandatory YES/NO filters:
- ✅ Python + SQL (strong hands-on)
- ✅ LLM experience (RAG + Prompt Engineering)
- ✅ Built GenAI/LLM applications (real projects)
- ✅ PyTorch or TensorFlow
- ✅ Data engineering exposure
- ✅ Cloud (AWS/Snowflake)
✅ Strong preference:
- ✅ Agentic AI frameworks
- ✅ Knowledge graph / Neo4j
- ✅ Kafka / real-time systems
- ✅ LLMOps / MLOps
- ✅ Banking / regulated domain

Other Requirements

null

#development#AI#LLM#Wealth Management#Ontology#Knowledge Graph#Agentic Workflows#SageMaker#Python#SQL#Snowflake#AWS#Banking#regulated-environment