MLOps Engineer
Abu Dhabi Emirate, United Arab Emirates · Full Time
Be the first to apply
- Experience
- 3+ yrs
- Salary
- —
- Openings
- 1
- Posted
- 1 week ago
- Work mode
- In office
- Resume
- Required to apply
Sign in to tell us what does and doesn't work for you here — it sharpens every match we show you.
Job description
About First Tech
First Tech is a technology-driven company dedicated to creating, scaling, and delivering innovative digital platforms primarily for the financial services sector and other industries. Our expertise combines robust technology, product knowledge, and a strong grasp of customer needs to design solutions that simplify complex workflows and provide seamless digital experiences. Our platforms prioritize scalability, reliability, and impact, empowering businesses and customers to confidently navigate the evolving digital environment.
With a vision to accelerate digital transformation, First Tech brings together advanced engineering, product innovation, and a collaborative culture that fosters impactful modern solutions. By collaborating with forward-looking organizations and innovating with technology-based products, we aim to remodel industries and enhance everyday experiences, cultivating an inclusive, innovation-driven work environment.
Job Purpose
We are seeking an MLOps Engineer to develop and manage the infrastructure powering our Large Language Model (LLM) applications in production. This role involves overseeing GPU-backed inference systems and ensuring secure, compliant deployment pipelines.
Key Responsibilities
- Deploy, manage, and scale container orchestration platforms like Kubernetes that run GPU-enabled LLM workloads.
- Design and provision multi-cloud infrastructure using Infrastructure as Code methodologies.
- Enhance LLM inference performance by optimizing latency, throughput, and operational costs.
- Establish and maintain continuous integration and deployment pipelines for containerized applications.
- Create retrieval and caching systems to support production LLM services.
- Monitor infrastructure and lead incident response actions for model serving endpoints.
- Develop evaluation pipelines aimed at detecting quality regressions before releases.
- Ensure strict adherence to security and compliance standards across the infrastructure and data workflows.
- Coordinate and automate end-to-end machine learning and data workflows.
Required Qualifications and Skills
- Minimum of 3 years experience in MLOps, LLMOps, DevOps, or related infrastructure/platform engineering roles.
- Expertise in container orchestration including GPU scheduling, node pool configuration, autoscaling, network policies, and workload identities, especially Kubernetes.
- Proficient with multi-cloud environments such as AWS, Google Cloud Platform, or Azure, encompassing compute, networking, databases, and storage.
- Strong experience with Infrastructure as Code tools for multi-environment deployments, such as Terraform.
- Understanding of cloud security principles including identity and access management (IAM), virtual private clouds (VPC), encryption, and audit logging.
- Knowledge in observability practices including logging, monitoring, tracing, and service level objective (SLO) management.
- Familiarity with LLM inference serving frameworks like vLLM, Text Generation Inference (TGI), Triton, or equivalents.
- Skills in inference optimization techniques including quantization, batching, and key-value cache management.
- Experience developing evaluation frameworks for LLM quality and regression testing, such as LangSmith or custom solutions.
- Understanding of security and compliance requirements relevant to government or regulated sectors.
Benefits
- Competitive compensation packages with performance-related bonuses.
- Comprehensive health and wellness programs.
- Opportunities for professional growth and skill development.
- Involvement in high-impact projects alongside cross-disciplinary teams.
- Cultivation of a collaborative culture that values innovation and personal ownership.
Work Culture and Inclusion
At First Tech, we foster an environment where employees are empowered to excel and expand their capabilities. Our culture is founded on principles of ownership, teamwork, and continuous learning. You will have the chance to contribute to projects that significantly influence digital experiences in financial services. We are proud to be an equal opportunity employer committed to diversity and inclusion, welcoming applicants from all backgrounds who are excited by this role.