Senior Software Engineer

Ml Inferencewhy
Graz, Austria
2 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English
Experience level
Senior

Job location

Graz, Austria

Tech stack

Geographic Information Systems
API
Artificial Intelligence
Amazon Web Services (AWS)
Program Optimization
Continuous Integration
Distributed Systems
Python
PostgreSQL
Machine Learning
AI Platforms
Kubernetes
Build Tools
Machine Learning Operations
Hardware Infrastructure

Job description

you'll build the orchestration layer that powers our geospatial AI platform. You'll work at the intersection of distributed systems and machine learning, enabling customers to train custom detection models and run inference at scale on imagery spanning continents.What you'll doBuild and optimize ML orchestration pipelines that coordinate model training and inference across distributed worker poolsDesign resilient, high-throughput services that process terabytes of geospatial imagery through GPU-accelerated inferenceDevelop the APIs and abstractions that allow customers to chain, filter, and compose AI models for complex detection workflowsCollaborate with ML Researchers to put new models in productionTackle memory optimization, GPU autoscaling, and resource scheduling challenges unique to large-scale imagery processingYOUR PROFILEStrong practical knowledge of Python with experience building production systemsExperience designing and operating distributed systems or data pipelinesFamiliarity

Requirements

with async processing patterns, task queues, and worker pool architecturesSolid understanding of PostgreSQL and data modelingStrong software engineering fundamentals: testing, CI/CD, observability, reliabilityYou're outcome-oriented and comfortable navigating ambiguity to deliver resultsIdeally:Experience with ML infrastructure, model serving, or training pipelinesHands-on experience with Kubernetes in production environmentsFamiliarity with GPU workloads and the unique challenges of ML at scaleExperience with geospatial data formats (GeoTIFF, COG, STAC) or imagery processingBackground deploying systems in regulated or air-gapped environmentsTech StackPython, FastAPIPostgreSQL, RedisDocker, Kubernetes (EKS, K3S)AWS (with on-prem and edge deployment targets)GPU infrastructure for ML inferenceWhy join us?Real impact at scale: Your work powers AI inference across imagery of entire countries, supporting defence, intelligence, and humanitarian applicationsDiverse deployment challenges

Benefits & conditions

Build systems that run in AWS, on customer infrastructure, or on a laptop in the fieldeach with unique constraintsGrowth trajectory: Join ahead of our Series B as we expand into new markets and scale the platformStrong technical culture: Work alongside ML Engineers, GIS specialists, and infrastructure experts solving novel problems in geospatial AIHealthy work-life balance with flexible working arrangementsCompetitive compensation with personalized benefits including learning opportunities, mental well-being programs, and healthcareThe minimum salary is 56.000,-- gross per year. The effective salary depends on qualification and experience and may be significantly higher!

Apply for this position