Software Engineer (ML systems)
Core
Design, deploy, and maintain scalable, production-grade ML systems for AI research projects involving LLMs and multimodal models.
Role type
Senior IC ML systems engineer
Builds
Scalable backend services, APIs, and CI/CD pipelines for model serving in cloud or HPC environments
Domain
Artificial Intelligence, Large Language Models (LLMs), Multimodal models, Earth Observation, Videoconferencing
Deliverable
production ML models
Required skills
Python, Cloud Services (AWS/GCP), Model serving frameworks (FastAPI, BentoML, vLLM, Triton), CI/CD tools, Relational databases (PostgreSQL), REST API design, Microservices architecture, Authentication/authorisation (JWT, OAuth), Networking concepts (proxies, load balancing)
Preferred skills
Docker, Linux, LLM-specific frameworks (Langchain, NVIDIA NeMo), ML/DL frameworks (PyTorch), LLMOps pipeline
Technologies
Python, AWS, GCP, RunPod, Lambda Labs, FastAPI, BentoML, vLLM, Triton, PostgreSQL, Docker, Linux, Langchain, NVIDIA NeMo, PyTorch
Responsibilities
Develop scalable backend services and APIs for model serving; Own CI/CD, testing, deployment, and monitoring of ML systems; Optimise performance across the stack (data pipelines, GPU workloads, inference latency); Collaborate with researchers to translate prototypes into production systems; Contribute to engineering best practices; Support open-source releases
Seniority
Mid-to-Senior, hands-on IC