Gen AI Engineer - Banking
Unison Group Open · verified Oct 22, 2026 At a glance
Mid-level AI Engineering role at Unison Group. Singapore · contract.
Pay not stated AI Engineering salary
aimlroles summary, based on the employer's posting.
What you'll do
- Build production LLM applications using retrieval, embeddings, vector stores and structured outputs
- Develop conversational access to reports and KPIs, including text-to-SQL through a semantic layer
- Add row-level permissions and human checks to AI results, with banking controls such as audit trails and privacy safeguards
- Test answer quality, SQL accuracy and hallucinations, then run guardrails through automated CI/CD
- Parse SQL, PL/SQL, SAS and Python code to extract lineage
What you bring
- At least eight years in software or data engineering, including two or more focused on LLM applications
- At least three years working in banking or regulated financial services
- Strong Python and SQL skills, plus experience with enterprise-scale warehouse data
- Experience building in regulated settings with authentication, access entitlements, audit logs and data privacy
Who this fits
This mid-level contractor role is based onsite in Singapore. It suits an engineer with substantial software or data experience who has built LLM applications for banking or other regulated financial services.
From the employer
We are looking for Gen AI Engineer with 8+ years in software or data engineering, including 2+ on LLM applications and 3+ in banking or regulated financial services.
Must-have skills
Banking and controls
• Building software in regulated environments: authentication, entitlements, audit logging and data privacy.
• Applying row-level access and human review steps to AI outputs.
Generative AI engineering
• LLM applications beyond proof of concept: RAG, embeddings, vector stores and structured outputs.
• Text-to-SQL over a semantic layer; conversational retrieval of reports and KPIs.
• Agent frameworks such as LangGraph or LlamaIndex.
• Evaluation: accuracy, SQL correctness, hallucination testing and guardrails, automated in CI/CD.
• Code parsing and lineage extraction for SQL, PL/SQL, SAS and Python (e.g. sqlglot, ANTLR).
Software and data engineering
• Strong Python and SQL.
• Working with enterprise data at warehouse scale.
• Git, CI/CD and MLflow.
Good-to-have skills
• Enterprise LLM platforms: Azure OpenAI, AWS Bedrock or Vertex AI.
• Databricks Mosaic AI or Genie.
• Visualization libraries (Plotly, ECharts, Vega) and Qlik or Power BI APIs.
Certifications (preferred): Databricks Generative AI Engineer Associate; Azure AI Engineer; AWS ML Specialty.