Platform Lead

Job description

Platform Lead 
Remote
$160,000-210,000

The **Platform Lead** will be responsible for designing and implementing distributed systems that incorporate large language models (LLMs) and agent orchestration frameworks into our platform. This role will involve close collaboration with engineering, data science, and DevOps teams to deliver secure, scalable, reliable, and cost-efficient solutions ready for production.

Key Responsibilities of the Platform Lead:

• **System Architecture & Design**: Create and optimize distributed systems and microservices, weighing the trade-offs among latency, throughput, and scalability.
• **Integration of Agentic Frameworks**: Implement and refine orchestration frameworks such as LangChain, AutoGen, and Haystack; assess both open-source and enterprise options.
• **LLM Integration**: Work with APIs from providers like OpenAI, Anthropic, Mistral, and Cohere; oversee the management of model hosting environments (e.g., Hugging Face, vLLM, Sagemaker, Azure).
• **Development of Tools & Plugins**: Create and maintain connectors to facilitate agent interactions with APIs, databases, and specialized tools.
• **Security & Compliance Management**: Implement best practices around RBAC, secrets management, auditing, and data governance.
• **DevOps/MLOps**: Manage and deploy workloads using Docker and Kubernetes, create CI/CD pipelines, and ensure efficient monitoring, observability, and cost management.

Qualifications for the Platform Lead:

• A minimum of 6 years of experience in software/platform engineering, including at least 2 years in a leadership role.
• Demonstrated expertise in the architecture of distributed systems and microservices.
• Practical experience with agentic orchestration frameworks (e.g., LangChain, AutoGen, Haystack).
• Familiarity with LLM APIs and hosting services.
• In-depth knowledge of cloud infrastructure technologies (AWS, Azure, or GCP).
• Experience with containerization technologies (Docker, Kubernetes) and CI/CD practices.
• Solid understanding of security and compliance principles (RBAC, secrets management, governance).