Senior AI and Software Engineer

MXHL PTE. LTD.; Singapore; On-site; SGD 160,000 - 190,000; Full time

Job summary

MXHL PTE. LTD. in Singapore is hiring a Senior AI & Software Engineer to architect and build the core intelligence powering real‑time job assignment, routing, and driver‑matching at scale.

You will design distributed systems, production‑grade ML pipelines, and shape the technical direction of a fast‑growing logistics platform using AWS, Django, and modern microservice patterns.

Qualifications

• Strong CS fundamentals: algorithms, data structures, distributed systems.
• Expert Python with Django production experience.
• Deep AWS cloud architecture and infra design.
• Experience with ML models in production environments.
• Strong RESTful API, microservices, and asynchronous systems knowledge.

Responsibilities

• Architect and implement backend services in Python/Django.
• Design scalable, fault-tolerant systems on AWS and related services.
• Build high-performance APIs for real-time decisioning and driver matching.
• Develop async pipelines using Celery, SQS or equivalents.
• Lead AI-driven job assignment engine design with ML pipelines.

Skills

Python

Django

AWS

RESTful API design

Microservices

Asynchronous systems

CI/CD

Docker

Tools

Celery

SQS

CloudFormation

EC2

ECS

Job description

Own the Architecture. Build the Intelligence. Scale the Network.
uParcel operates one of Singapore’s largest last‑mile delivery networks, and we are evolving our platform into a fully autonomous, AI‑driven logistics engine. We’re hiring a Senior AI & Software Engineer to architect and build the core intelligence that powers real‑time job assignment, routing efficiency, and driver‑matching logic at scale.
This is a high‑impact engineering role for someone who wants to design distributed systems, build production‑grade ML pipelines, and shape the technical direction of a fast‑growing logistics platform.

Core Responsibilities

System Architecture & Backend Engineering Architect and implement backend services using Python, Django, and modern microservice patterns Design scalable, fault‑tolerant systems deployed on AWS (EC2, ECS/Lambda, RDS, S3, CloudWatch, API Gateway, IAM, containers) Build high‑performance APIs for real‑time decisioning, driver‑job matching, and operational workflows Implement asynchronous processing pipelines using Celery, SQS, or equivalent AI/ML Engineering Lead the design and development of uParcel’s AI‑driven job assignment engine, incorporating: Real‑time geospatial data Driver availability, historical performance, and behavioral patterns Delivery SLAs, urgency, and route constraints Predictive ETA and load balancing models Build ML pipelines for training, evaluation, and deployment (batch + real‑time inference) Implement model monitoring, drift detection, and continuous retraining workflows. Data Engineering & Infrastructure Design data schemas and pipelines to support high‑volume event ingestion Work with geospatial datasets, map APIs, and routing algorithms Optimize query performance on relational and NoSQL datastores Ensure observability across services (metrics, tracing, structured logs) Technical Leadership Drive architectural decisions and enforce engineering best practices Conduct deep technical code reviews and mentor mid‑level engineers Collaborate with product, operations, and data teams to translate business logic into deterministic, scalable systems Own end‑to‑end delivery of features from design to production rollout.

Required Technical Expertise

Strong computer science fundamentals: algorithms, data structures, distributed systems Expert‑level proficiency in Python and production experience with Django Deep understanding of AWS cloud architecture and infrastructure design Experience building and deploying ML models in production environments Strong knowledge of RESTful API design, microservices, and asynchronous systems Familiarity with geospatial computation, routing algorithms, or optimization models Experience with CI/CD pipelines, containerization (Docker), and IaC (CloudFormation) Ability to reason about system performance, scalability, and reliability

Bonus Skills

Experience with reinforcement learning or real‑time decision engines Background in logistics, fleet optimization, or marketplace matching systems Knowledge of graph algorithms, heuristics, or constraint‑solving techniques