Senior MLOps Engineer

Fortytwo https://fortytwo.network is a decentralized AI protocol on Monad that leverages idle consumer hardware for swarm inference. It enables Small Language Models to achieve advanced multi-step reasoning at lower costs, surpassing the performance and scalability of leading models. RESPONSIBILITIES: - Deploy scalable, production-ready ML services with optimized infrastructure and auto-scaling Kubernetes clusters. - Optimize GPU resources using MIG (Multi-Instance GPU) and NOS (Node Offloading System). - Manage cloud storage (e.g., S3) to ensure high availability and performance. - Integrate state-of-the-art ML techniques, such as LoRA and model merging, into workflows: - Work with SOTA ML codebases and adapt them to organizational needs. - Integrate LoRA (Low-Rank Adaptation) techniques and model merging workflows. - Deploy and manage large language models (LLM), small language models (SLM), and large multimodal models (LMM). - Serve ML models using technologies like Triton Inference Server. - Leverage solutions such as vLLM, TGI (Text Generation Inference), and other state-of-the-art serving frameworks. - Optimize models with ONNX and TensorRT for efficient deployment. - Develop Retrieval-Augmented Generation (RAG) systems integrating spreadsheet, math, and compiler processors. - Set up monitoring and logging solutions using Grafana, Prometheus, Loki, Elasticsearch, and OpenSearch. - Write and maintain CI/CD pipelines using GitHub Actions for seamless deployment processes. - Create Helm templates for rapid Kubernetes node deployment. - Automate workflows using cron jobs and Airflow DAGs. REQUIREMENTS: - Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field. - Proficiency in Kubernetes, Helm, and containerization technologies. - Experience with GPU optimization (MIG, NOS) and cloud platforms (AWS, GCP, Azure). - Strong knowledge of monitoring tools (Grafana, Prometheus) and scripting languages (Python, Bash). - Hands-on experience with CI/CD tools and workflow management systems. - Familiarity with Triton Inference Server, ONNX, and TensorRT for model serving and optimization. PREFERRED: - 5+ years of experience in MLOps or ML engineering roles. - Experience with advanced ML techniques, such as multi-sampling and dynamic temperatures. - Knowledge of distributed training and large model fine-tuning. - Proficiency in Go or Rust programming languages. - Experience designing and implementing highly secure MLOps pipelines, including secure model deployment and data encryption. WHY WORK WITH US: At Fortytwo, we are building a research-driven, decentralized AI infrastructure that prioritizes scalability, efficiency, and sustainability. Our approach moves beyond centralized AI constraints, applying globally scalable swarm intelligence to enhance LLM reasoning and problem-solving capabilities. - Engage in meaningful AI research – Work on decentralized inference, multi-agent systems, and efficient model deployment with a team that values rigorous, first-principles thinking. - Build scalable and sustainable AI – Design AI systems that reduce reliance on massive compute clusters, making advanced models more efficient, accessible, and cost-effective. - Collaborate with a highly technical team – Join engineers and researchers who are deeply experienced, intellectually curious, and motivated by solving hard problems. We’re looking for individuals who thrive in research-driven environments, value autonomy, and want to work on foundational AI challenges.