Senior MLOps Engineer (LLMOps)

Location: London, United Kingdom; hybrid model with attendance at the London office 3 days a week

Company

hirify.global Technologies is a dual-use technology company building Acra, an infrastructure-agnostic secure-enclave platform for protecting critical data and supporting secure government and commercial workflows.

What you will do

• Design, deploy, and manage production LLM services, agentic applications, and supporting AI workloads in high-throughput Kubernetes clusters.
• Automate containerized deployments, scalable inference endpoints, and blue/green or canary releases through CI/CD pipelines.
• Operate and maintain multi-step agentic workflows, including tool execution, state management, and multi-agent coordination.
• Triage and resolve issues across AI application logic, orchestration frameworks, external API integrations, and cloud infrastructure.
• Build monitoring and evaluation frameworks for accuracy, drift, latency, cost, hallucinations, and trace-level agent observability.
• Monitor AI data pipelines and optimize feature stores, vector indexing, embeddings, GPU/CPU utilization, autoscaling, memory, infrastructure costs, time-to-first-token, and throughput.

Requirements

• 3+ years of experience in MLOps, LLMOps, Platform Engineering, AI Infrastructure, or SRE focused on machine learning workloads.
• Hands-on experience managing and deploying complex containerized applications on Kubernetes, including EKS, GKE, AKS, or bare metal, at scale.
• Strong proficiency in Python for backend automation, system debugging, custom tooling, and integration development.
• Experience with monitoring and logging tools such as Prometheus, Grafana, Datadog, or OpenTelemetry, plus LLM-specific tracing and evaluation platforms such as LangSmith, Phoenix/Arize, Langfuse, or TruLens.
• Familiarity with CI/CD tools such as GitHub Actions, GitLab CI, or ArgoCD, and Infrastructure as Code tools such as Terraform or Pulumi.
• Deep operational understanding of agentic architectures, prompt chaining, function calling, tool execution, and non-deterministic application behavior.

Nice to have

• Experience operating Retrieval-Augmented Generation pipelines and production vector databases such as Pinecone, Qdrant, Milvus, pgvector, or Weaviate.
• Exposure to agent development and orchestration frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, or CrewAI.
• Experience with high-performance LLM serving engines and frameworks such as vLLM, TGI, Ollama, or TensorRT-LLM.
• Understanding of AI security practices including prompt-injection mitigation, data privacy, PII masking, rate limiting, and cost guardrails.

Culture & Benefits

• Hybrid work setup with collaboration in the London office.
• Equity, competitive salary, employer pension contributions, and private health insurance.
• Gym membership and company retreats and meetups supporting work-life balance.
• Culture focused on inclusivity, compassion, flexibility, collaboration, and mutual trust.