OPEN POSITION

MLOps / DevOps

The MLOps / DevOps Engineer is a key specialist bridging our ML teams and production infrastructure.

Apply now

Responsibilities

Build robust, seamless and versatile CI/CD pipelines for both general services and ML modules

Create infrastructure for development process, ML training and inference, and software distribution

Manage K8s clusters

Constantly improve observability and stability of the whole system

Come up with and implement ideas about making life of developers and data scientists easier

Developing and managing Helm charts for deploying GPU workloads on external providers

Support real-time multimodal inference workloads (speech-tech, llm) across distributed clusters.

Requirements

5+ years in MLOps, DevOps, or SRE roles with hands-on experience in ML related tasks

Extensive knowledge and hands-on experience with GCP/AWS

Wide range of expertise in K8s itself and related tools like Helm, Vault, ingress-nginx, etc

Infrastructure: IaC with Pulumi and/or Terraform, experience managing GPU nodes

Experience with some of Grafana, Prometheus, ELK, OpenTelemetry, Sentry

Experience with management of ML training infrastructure with DVC or similar tools

Experience with serving large models in streaming mode: LLMs, ASR, TTS with 50M+ parameters

Experience with NVIDIA Triton Inference Server. Distributed LLM hosting expertise is a great advantage

Experience with building ML inference platform on Kubernetes, e.g. using KServe

Model optimization experience (TensorRT, cuda graphs) is a great advantage

Comfortable in uncharted waters. We are building something new. Things change quickly. We need you to learn technologies and patterns quickly

Ability to see the long term. We don’t want you to sacrifice the future for the present. We want you to choose technologies and approaches based on the end goals.

Why join us?

Experienced team, Aiphoria is formed by a team of enthusiastic professionals who created award-winning devices, voice assistants and other AI-driven products for BigTech corporations

Cutting-edge technologies, we build a technology using our areas of expertise including Computer Vision, Speech Technologies, Natural Language Understanding, Generative AI incl. LLM and Diffusion models

Rapid career progression, facilitated by our team of seasoned senior professionals who hail from prestigious, industry-leading companies

Remote work opportunities from Europe / US

Company has prominent clients with an opportunity for you to work on different projects and/or to be involved in developing our proprietary own products

Competitive compensation surpassing market standards

A company with entrepreneurial spirit. We offer a unique mix of a secure workspace thanks to the big clients raised along with a true start-up culture!

Responsibilities

Build robust, seamless and versatile CI/CD pipelines for both general services and ML modules

Create infrastructure for development process, ML training and inference, and software distribution

Manage K8s clusters

Constantly improve observability and stability of the whole system

Come up with and implement ideas about making life of developers and data scientists easier

Developing and managing Helm charts for deploying GPU workloads on external providers

Support real-time multimodal inference workloads (speech-tech, llm) across distributed clusters.

Requirements

5+ years in MLOps, DevOps, or SRE roles with hands-on experience in ML related tasks

Extensive knowledge and hands-on experience with GCP/AWS

Wide range of expertise in K8s itself and related tools like Helm, Vault, ingress-nginx, etc

Infrastructure: IaC with Pulumi and/or Terraform, experience managing GPU nodes

Experience with some of Grafana, Prometheus, ELK, OpenTelemetry, Sentry

Experience with management of ML training infrastructure with DVC or similar tools

Experience with serving large models in streaming mode: LLMs, ASR, TTS with 50M+ parameters

Experience with NVIDIA Triton Inference Server. Distributed LLM hosting expertise is a great advantage

Experience with building ML inference platform on Kubernetes, e.g. using KServe

Model optimization experience (TensorRT, cuda graphs) is a great advantage

Comfortable in uncharted waters. We are building something new. Things change quickly. We need you to learn technologies and patterns quickly

Ability to see the long term. We don’t want you to sacrifice the future for the present. We want you to choose technologies and approaches based on the end goals.

Why join us?

Experienced team, Aiphoria is formed by a team of enthusiastic professionals who created award-winning devices, voice assistants and other AI-driven products for BigTech corporations

Cutting-edge technologies, we build a technology using our areas of expertise including Computer Vision, Speech Technologies, Natural Language Understanding, Generative AI incl. LLM and Diffusion models

Rapid career progression, facilitated by our team of seasoned senior professionals who hail from prestigious, industry-leading companies

Remote work opportunities from Europe / US

Company has prominent clients with an opportunity for you to work on different projects and/or to be involved in developing our proprietary own products

Competitive compensation surpassing market standards

A company with entrepreneurial spirit. We offer a unique mix of a secure workspace thanks to the big clients raised along with a true start-up culture!

© 2022—2024 Aiphoria

UK, Cyprus, Portugal, UAE