Senior AI Engineer (Production GenAI and ML Systems)

Who we are

Headquartered in Singapore, SATS Ltd. is one of the world’s largest providers of air cargo handling services and Asia’s leading airline caterer. SATS Gateway Services provides airfreight and ground handling services including passenger services, ramp and baggage handling, aviation security services, aircraft cleaning and aviation laundry. SATS Food Solutions serves airlines, institutions, and operates central kitchens with large-scale food production and distribution capabilities for a wide range of cuisines. SATS is present in the Asia-Pacific, the Americas, Europe, the Middle East and Africa, powering an interconnected world of trade, travel and taste. Following the acquisition of Worldwide Flight Services (WFS) in 2023, the combined SATS and WFS network operates over 215 stations in 27 countries. These cover trade routes responsible for more than 50% of global air cargo volume. SATS has been listed on the Singapore Exchange since May 2000. For more information, please visit www.sats.com.sg

The Role

We are hiring a Senior AI Engineer in our AI COE. The Senior AI Engineer is responsible for building and scaling production-grade AI/ML, GenAI, Simulation, Search systems. This role bridges the gap between data science and engineering by ensuring models are deployed, monitored, and maintained reliably in real-world environments.

Location: India/Singapore

Some international travel may be required.

Key Responsibilities

ML System Engineering

· Design and implement scalable ML pipelines (batch & real-time)

· Build model serving infrastructure using APIs and microservices

· Optimize inference performance and latency

MLOps & Automation

· Implement CI/CD pipelines for ML workflows

· Manage model versioning, monitoring, and retraining pipelines

· Ensure reproducibility and reliability of ML systems

Platform Integration and Enablement

· Integrate ML systems with enterprise data platforms

· Collaborate with AI CoE teams on platform capabilities

· Enable self-service ML deployment capabilities

· Provide reusable building blocks for AI teams

· Enable rapid experimentation and deployment

· Collaborate with AI/ML teams to accelerate GenAI adoption

GenAI Platform Development

· Build and maintain RAG pipelines and LLM orchestration frameworks

· Develop reusable GenAI services and APIs

· Enable multi-agent and agentic workflows

Infrastructure & Systems

· Implement scalable model serving infrastructure (vLLM, Triton, APIs)

· Manage vector databases and embedding pipelines

· Optimize performance and cost of LLM systems

Innovation

· Evaluate emerging GenAI tools and frameworks

· Drive adoption of best practices in LLMOps

Collaboration

· Work closely with data scientists to productionize models

· Partner with platform teams for scalability and performance

Educational Qualifications

· Bachelor/ MSc / PhD in Computer Science, Mathematics or related field

· Ongoing commitment to training and professional development in AIML, GenAI, Aviation Domain,

Cargo handling, Ground handling milestones, Ground Freight and Food solutions.

Relevant Skills and Experience

· 6–10+ years in ML engineering / software engineering

· Strong Python + FastAPI

· Strong expertise in: Docker, Kubernetes, MLflow / Kubeflow, CI/CD pipelines

· Experience in real-time and batch inference systems

Personal Characteristics & Behaviours

· Strong engineering mindset

· Ownership and accountability

· Attention to scalability and reliability