AI Platform Engineer / MLOps Engineer

McGregor Boyall is recruiting for a senior AI Platform / MLOps Engineer to join a premier global quantitative investment firm, focusing on infrastructure, systems, and MLOps within AI/LLM domains.

• Strong background as a Platform, MLOps, or Infrastructure Engineer with deep Unix and Kubernetes expertise handling containerized environments and GPU workloads.
• Proven hands-on experience hosting, operating, and scaling LLM systems and production RAG pipelines in live environments.
• Strong hands-on knowledge of AWS including networking fundamentals, IAM, cloud security, and orchestration.
• Solid Python skills sufficient to write custom infrastructure tasks, build production APIs, and handle service integration.
• Experience tuning vector databases with understanding of context/token constraints, embeddings, and output reliability.

Nice to have:

• Hands-on experience with agentic AI systems and workflow orchestration frameworks.
• Familiarity with inference optimization, model serving platforms, and LLM evaluation/quality measurement frameworks.
• AWS or Kubernetes (CKA/CKAD) certifications.

Key Responsibilities:

• Build, scale, and maintain GPU-context Kubernetes environments and Unix infrastructure hosting production LLM workloads.
• Integrate model serving endpoints into core application services, maintaining production-grade APIs.
• Manage the performance, scalability, data freshness, and retrieval quality of vector databases and ingestion pipelines.
• Implement end-to-end monitoring, tracing, prompt versioning, and fallback mechanisms for critical AI endpoints.
• Own service rollouts, deprecation, latency optimization, and operational incident response for high-throughput AI services.

At McGregor Boyall Associates we process candidate data respecting privacy and for legitimate interests, including contacting candidates about employment opportunities. Candidates can opt out of future contacts by emailing [email protected].