Remote Senior AI Engineer – Edge-Cloud Security

Ent; United States; Remote; USD 180,000 - 230,000; Full time

Benefits offered by this job

Equity

Remote-friendly across North America

Medical, dental, vision coverage

Flexible PTO

Parental leave

Lifestyle budget

Home office stipend

Job summary

Ent is seeking a Senior AI Engineer to deploy and manage AI models on endpoints, enabling real-time decisions as people and AI agents work together. You will move models from researchers to production, ensure safe deployment with gates, and monitor performance in both edge and cloud environments.

You will own end-to-end pipelines, retraining cycles, and evaluation strategies, while collaborating with security teams to protect users and agents.

Qualifications

• Own and design whole systems end to end across roles or companies.
• Experience training, evaluating and deploying your own models in production; relying on more than just LLM APIs.
• Translate other people’s algorithms into correct, tested production code.
• Strong grasp of model evaluation, including detecting regressions and deciding when to ship.
• Proficient in Python and at least one systems/backend language (C/C++, Java, Rust or Go).
• Curiosity about AI, security, and future directions; comfortable with ambiguity.

Responsibilities

• Take models and algorithms from scientists into production and reimplement them correctly (e.g., Python to C++/Java) with parity verification.
• Own models after launch: retraining, monitoring and evaluation to free researchers for new work.
• Design evaluation and release gates to ensure safe shipping and explain metric shifts.
• Build production monitoring for model quality, including drift detection and retrain triggers.
• Run inference with tight latency/memory budgets on endpoints and in the cloud, using quantization, distillation, batching and caching.
• Build pipelines connecting cloud and endpoint layers to deliver contextual data back to endpoints.
• Create infrastructure for training and experimentation (datasets, reproducible training, CI/CD) and keep it simple.

Skills

Python

C/C++

Java

Rust

Edge inference

LLM APIs integration

Tools

ONNX Runtime

llama.cpp

TensorRT

OpenVINO

Job description

Ent is seeking a Senior AI Engineer to deploy and manage AI models on endpoints, enabling real-time decisions as people and AI agents work together. You will move models from researchers to production, ensure safe deployment with gates, and monitor performance in both edge and cloud environments.

You will own end-to-end pipelines, retraining cycles, and evaluation strategies, while collaborating with security teams to protect users and agents.