Lead DevOps / AI Engineer (SRE)

Trine Partners is hiring a Lead DevOps / AI Engineer for its Site Reliability Engineering team. The role sits between traditional SRE work and AI operations: you will keep high availability cloud infrastructure running, and at the same time build the pipelines and tooling that put machine learning models and LLMs into production and keep them there.

This is a remote position working United States Eastern Time, on a rotational shift pattern.

What you will do

Infrastructure and operations

• Design, build and maintain scalable, resilient cloud infrastructure on AWS, defined as code.

• Run and tune Kubernetes clusters for containerised applications and for model serving.

• Hold the line on availability, performance and disaster recovery across microservices and distributed systems.

AIOps and observability

• Bring anomaly detection, predictive alerting and automated root cause analysis into the telemetry stack, working with Datadog, Prometheus and Grafana.

• Build self healing workflows and assisted remediation tooling that brings mean time to resolution down.

MLOps and pipeline automation

• Build and maintain CI/CD and MLOps pipelines for training, validating and deploying models, including large language models.

• Tune inference performance, GPU and CPU utilisation, and the cost of running AI workloads in production.

Reliability, security and cost

• Run chaos engineering exercises and blameless post mortems, and turn the findings into platform changes.

• Enforce access controls, security practices and compliance requirements across pipelines and infrastructure.

• Watch cloud spend and GPU compute cost, and act on it.

Technical leadership

• Lead the design of reliability and AI infrastructure work rather than only implementing it.

• Guide the team on automation, observability and MLOps practice, and own the technical decisions that follow.

What we are looking for

• 8 or more years in DevOps, SRE or cloud platform engineering, with hands on exposure to AI and ML deployment pipelines.

• Deep experience with AWS, GCP or Azure, plus Kubernetes and Docker in production.

• Infrastructure as code with Terraform, Pulumi or CloudFormation.

• Strong coding in Python, Go or Bash. This is a build role, not a configure role.

• CI/CD pipelines built with GitHub Actions, GitLab CI or Argo CD.

• Observability with Prometheus, Grafana, Datadog or OpenTelemetry.

Nice to have

• MLOps tooling: Kubeflow, MLflow, Ray, vLLM, Triton Inference Server.

• Deploying or fine tuning large language models and generative AI services in production.

• Vector databases such as Pinecone, Milvus or Qdrant, and frameworks like LangChain or LlamaIndex.

Working pattern

• Fully remote.

• United States Eastern Time, rotational shifts.

• We are looking for people who can start immediately or within 15 to 20 days.

Compensation

Up to 20 LPA. There is room to discuss for the right person, so apply if the role fits and the number is close.