Key Skills

Job Description

Company Description Imprima specializes in reducing the stress of managing large and complex deals with numerous moving parts. Our core values of security, reliability, service, and innovation ensure our clients can focus on their deals with complete peace of mind, never worrying about data integrity. As pioneers of highly secure Virtual Data Rooms (VDRs) and self-service document management applications, our breakthrough AI technology keeps us at the forefront of the industry. Our advanced platform allows high-level stakeholders to access a wealth of reports, assign varied permissions and access rights, and provides admins with complete visibility into all document touch points — who viewed them, for how long, and any alterations made. Our AI features, including document Q&A and automated PII redaction, help deal teams find what matters across thousands of documents. Role Description We're looking for a Machine Learning Engineer to build, deploy and operate the ML systems behind our products, with a strong focus on our Azure cloud environment. You'll take models from prototype to production and keep them running reliably at scale. Typical projects may include: Writing clean, well-tested Python services and pipelines: APIs, batch jobs and data processing Deploying and operating ML services on Azure (AKS, Azure Container Apps, Azure Functions), using Managed Identity for secret-free access to resources Managing infrastructure as code with Terraform Building and maintaining CI/CD pipelines for model and infrastructure releases Containerizing ML workloads with Docker and running them on Kubernetes, including GPU workloads Setting up monitoring, alerting and tracing with Application Insights, and hardening existing production systems Operating our vector database in production: sharding, replication, backup and restore Working with research to optimize models for production inference (quantization, ONNX, vLLM/SGLang) This is an opportunity to own our ML systems from development through production. We're still shaping how AI engineering works at Imprima: the tooling, the standards, the way work moves from prototype to production. You'll help lay that foundation rather than just work within it, together with a small AI R&D team that gives you plenty of autonomy. Qualifications What You Need Bachelor's degree in computer science, engineering or a related field 4+ years of professional Python development: clean, typed and tested code Strong hands-on experience with Azure or another major cloud platform: managed Kubernetes, container platforms, serverless functions, identity and access management, and monitoring Docker and Kubernetes in production, including GPU workloads Experience building CI/CD pipelines Linux and bash scripting Self-sufficient and high-agency: you take ownership, make decisions and move things forward on your own Excellent communication skills in English, both written and spoken Nice To Have PyTorch experience Understanding of ML fundamentals: model evaluation, embeddings, LLM inference Model optimization and adaptation: ONNX, quantization, LoRA Experience with vector databases Serving LLMs with vLLM or SGLang .NET experience, ideally with Azure Functions (our frontend is .NET) Master's degree in computer science, AI or a related field

Core Responsibilities

Build, deploy, and operate production machine learning systems, including Python services and pipelines, cloud infrastructure, CI/CD, and containerized workloads on Azure. Improve reliability and inference performance through monitoring, vector database operations, and model optimization in collaboration with the research team.

Requirements

Requires a bachelor's degree in computer science, engineering, or a related field, plus at least four years of professional Python development experience. Candidates should have hands-on cloud experience, production Docker and Kubernetes experience including GPU workloads, CI/CD skills, Linux and Bash scripting, and strong English communication skills.