Model Optimization: Evaluate and implement fine-tuning strategies for open-source models (e.g., Llama 3, DeepSeek) when off-the-shelf APIs do not meet specific accuracy or privacy requirements.
Strategic Roadmap: Develop a technical AI roadmap that identifies high-ROI opportunities within the department and outlines the transition from pilot projects to scalable production systems.
Core AI Engineering: 3+ years of experience in AI application development with a strong focus on Large Language Models (LLMs) and Natural Language Processing (NLP).
...
Process vendors’ payments to ensure invoices are duly booked, with appropriate supporting documents and approvals
Perform month-end close activities & reporting, strictly adhere with closing timeline
Manage communications between finance team and all stakeholders (eg. Sales admin team, warehouse team, vendors etc.), ensure all queries and issues are addressed timely
...
Design and optimise cloud-agnostic AI architectures across AWS, Azure, GCP and VMware using containerisation, creating reusable APIs, microservices and AI components for consistent global deployment
Apply FinOps principles with guardrails and quotas to optimise AI models and pipelines for performance, latency, cost and scalability, ensuring predictable and efficient cloud spend across global operations
Embed explainability, responsible AI practices and governance controls into all AI solutions, ensuring compliance with global regulatory standards, data privacy laws and company risk frameworks
...
Solution Guidance & Quality Assurance: Partner with solution architects and engineering leads to shape designs (batch/stream, APIs, real-time scoring, vector stores/RAG, feature pipelines) and assure conformance to blueprint pre‑build, during build, and pre‑go‑live.
Risk, Controls & Compliance: Embed data quality, lineage, retention, encryption, and access controls. Ensure designs meet data privacy, model risk, and operational resilience requirements across jurisdictions.
Value Realisation & Metrics: Define measurable outcomes (e.g., time-to-model, reuse of data products/patterns, cost-to-serve) and track via OKRs; inform investment prioritisation through architecture insights.
...
Oversee the knowledge management efforts of codes and algorithm so as to enable code reusability and efficiently
Test and recommend new AI/ ML solutioning so as to support current and future possible use cases and oversee the curation of skills and courses suitable based on the jobs-skills-proficiency maps, and assessment rubrics
Build collaboration and partnerships by keeping abreast of the latest advancements in AI and ML technology so as to proactively identify, initiate and promulgate worthwhile engineering projects that could be maximise in similar use cases across the SAF
...
Define and implement the "Definition of Done" for AI using quantitative evaluation. Use evaluation tools (e.g. DeepEval) to score models on Faithfulness and Relevancy. Use these metrics to validate model upgrades and cost-optimisation experiments
Champion Deployment Autonomy: Containerise your solutions (e.g. Docker), define the infrastructure and deploy to our cloud resources via GitLab CI
Ensure governance by implementing deterministic guardrails (e.g. NeMo Guardrails, Guardrails AI) to enforce JSON output schemas and block non-compliant financial advice
...
Design, review, and revitalize instructional resources, module structures, and assessment rubrics aligned to emerging industry practices in Edge AI and distributed systems.
Embed competencies such as AI model optimization and edge analytics into curriculum delivery.
Develop hands-on lab modules involving embedded AI deployment, IoT telemetry pipelines, and hardware acceleration platforms.
...
Overall responsible for Financial Planning & Analysis section for AP Cluster markets by providing support on the day to day FP&A matters including but not limited to:
Design AI-ready data foundations including document ingestion, chunking, embeddings, vector search, hybrid search, re-ranking, knowledge graphs, metadata schemas, data lineage, source attribution, and access-aware retrieval.
Define and implement LLMOps / MLOps practices including model registry, prompt and pipeline versioning, evaluation frameworks, observability, monitoring of latency/quality/cost, model drift detection, retraining triggers, and deployment controls across DEV/UAT/PROD environments.
Design AI-ready data foundations for RAG and agentic AI, including document ingestion, chunking strategies, embedding pipelines, vector databases, hybrid search, re-ranking, metadata schemas, knowledge graph design, source attribution, data lineage, freshness controls, and access-aware retrieval.
...
Handle third-party related compliance matters where local input is required.
Act as an interface between the PSC and locations for nonstandard procurement requests, including leading and communicating information, issues and initiatives.
Support the PSC in expediting where direct local supplier contact is required or in case of issues.
...
Solution Guidance & Quality Assurance: Partner with solution architects and engineering leads to shape designs (batch/stream, APIs, real-time scoring, vector stores/RAG, feature pipelines) and assure conformance to blueprint pre‑build, during build, and pre‑go‑live.
Risk, Controls & Compliance: Embed data quality, lineage, retention, encryption, and access controls. Ensure designs meet data privacy, model risk, and operational resilience requirements across jurisdictions.
Value Realisation & Metrics: Define measurable outcomes (e.g., time-to-model, reuse of data products/patterns, cost-to-serve) and track via OKRs; inform investment prioritisation through architecture insights.
...
Define the client's AI transformation roadmap — prioritising initiatives by strategic value and execution readiness, managing board-level change, and ensuring sustainable adoption of agentic AI across the organisation.
Set architecture principles and make consequential technology choices for enterprise agentic AI programmes — spanning agent harness design, orchestration patterns, knowledge layer strategy, trust and safety frameworks, and AgentOps discipline; maintain sufficient hands-on depth to challenge assumptions, evaluate trade-offs, and direct senior engineers credibly.
Govern technical standards across the portfolio: orchestration and A2A patterns, knowledge layer architecture (RAG, MCP, Text-to-SQL, knowledge graphs), evaluation frameworks (golden datasets, LLM-as-judge, trajectory evals), and production readiness criteria — ensuring engineering disciplines are institutionalised, not improvised.
...
Working with cyber and information security teams, considering internal and external obligations required for solutions focused on mitigating fraud and scams
Facilitating communication between technical and non-technical stakeholders regarding AI projects and their impact on the applicable business value and risks
Designing, developing, and deploying AI Operations tools and frameworks – MLOps, LLMOps and DevOps
...