MLOps Engineer

AI71 is an industry leader in artificial intelligence, delivering innovative solutions that empower developers, businesses and governments to solve complex challenges. AI71 builds secure, enterprise-ready applications powered by cutting-edge technology—tailored for knowledge workers and sector-specific needs. AI71 bridges the gap between advanced AI and real-world impact. Guided by a strong commitment to research and responsibility, we create transformative solutions that drive progress and empower communities.

AI71 is an industry leader in artificial intelligence, delivering innovative solutions that empower developers, businesses and governments to solve complex challenges. AI71 builds secure, enterprise-ready applications powered by cutting-edge technology—tailored for knowledge workers and sector-specific needs. AI71 bridges the gap between advanced AI and real-world impact. Guided by a strong commitment to research and responsibility, we create transformative solutions that drive progress and empower communities.

As an MLOps Engineer you set the ML infrastructure and reliability strategy across AI71's platform, including how LLMs and other deep learning models are deployed, fine-tuned, and served  own architecture decisions across both SaaS and on-prem operating models, mentor engineers across teams, and drive multi-quarter ML infrastructure strategy. You are a force multiplier.

• Define ML infrastructure architecture across the platform: model deployment strategy (vLLM, Triton, or TGI), pipeline engineering (MLflow or Kubeflow), and cloud-native infrastructure across major cloud platforms (AWS, Azure, or GCP)
• Set direction for ML system reliability: monitoring, latency / throughput / availability targets, and incident response across research and production environments.
• Mentor senior MLOps engineers; raise the operational bar across multiple teams.
• Drive cross-team initiatives that improve inference performance and cost-efficiency, including distributed training frameworks (Deep Speed, FSDP, Accelerate).
• Partner with ML researchers, product, and engineering leadership on multi-quarter ML infrastructure strategy.
• Ensure ML infrastructure scales across managed SaaS and fully air-gapped on-prem deployments.

• 10+ years of MLOps, ML infrastructure, or machine learning engineering with history of architectural ownership.
• Proven track record architecting large-scale model deployment (including LLMs) and ML infrastructure at scale.
• Deep cloud expertise across major cloud platforms (AWS, Azure, or GCP) and strong Python proficiency
• Mentorship record — engineers you have grown now operate independently at higher levels.
• Deep comfort architecting ML systems that run in both managed SaaS and on-premises / disconnected air-gapped environments.
• Kubernetes at architectural depth — GPU scheduling, multi-tenancy, operators, and the failure modes of distributed workloads on shared clusters.
• Strong communication, stakeholder management, and decision-making skills, with a passion for building diverse, inclusive engineering teams.

• Ownership of production reliability at platform level: SLO definition, incident command, postmortem practice, and driving reliability improvements across teams rather than services.
• Architecture-level experience with distributed training and fine-tuning at scale (Deep Speed, FSDP, Megatron-LM), including cluster design, checkpointing strategy, and failure recovery.
• Deep GPU systems knowledge: CUDA, NCCL, interconnect topology (NVLink, Infini Band/RoCE), and diagnosing performance and communication problems across nodes.
• Model optimization strategy at portfolio level: quantization (FP8, AWQ, GPTQ), speculative decoding, with…