Senior Software Engineer (AI / LLMs)

📋 Description

• • Join a pioneering technology company at the forefront of intelligent infrastructure automation, leveraging the power of agentic AI to redefine enterprise IT support. As a Senior Backend Engineer, you will play a pivotal role in designing, building, and scaling the core backend systems that power an innovative AI-driven automation platform. This platform is engineered to serve enterprise IT teams and managed service providers globally, offering them unprecedented capabilities in managing mission-critical workloads.
• • This is a unique opportunity to be part of a small, rapidly growing organization where your contributions will have a direct and significant impact. You will be instrumental in building the foundational elements of a zero-to-one engineering initiative, focusing on large-scale AI orchestration. Your work will involve developing sophisticated distributed systems that seamlessly blend traditional infrastructure automation with cutting-edge technologies like Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and intelligent agents.
• • Your primary responsibility will be to design and implement robust backend services that enable complex intelligent agent workflows and facilitate autonomous infrastructure actions. This involves creating the intricate logic and systems that allow AI agents to understand, reason about, and act upon cloud infrastructure.
• • You will develop and maintain high-performance APIs and orchestration layers, primarily using Python and TypeScript. These services will serve as the connective tissue for integrating LLMs, sophisticated vector databases for semantic search, and comprehensive observability pipelines, ensuring the platform is both powerful and observable.
• • A key aspect of this role is building highly scalable systems designed to support LLM-based reasoning, retrieval, and decision-making processes across diverse cloud infrastructure environments. This requires a deep understanding of distributed systems architecture and performance optimization.
• • You will integrate with leading LLM platforms, including AWS Bedrock, to enable multi-model capabilities, allowing the platform to leverage the strengths of various AI models for different tasks.
• • Develop and manage data access layers and semantic search functionalities using state-of-the-art vector databases such as pgvector, Pinecone, or Qdrant. This will enable the AI to efficiently retrieve and utilize relevant information from vast datasets.
• • Construct and maintain comprehensive monitoring, testing, and CI/CD systems. This ensures the reliability, reproducibility, and continuous improvement of the AI workflows and the platform as a whole.
• • Collaborate closely and effectively with Product and DevOps teams. This includes actively participating in the design of architecture diagrams, planning and executing deployments, and diligently monitoring system health and performance.
• • You are expected to write clean, maintainable, and well-documented code, adhering strictly to security best practices and performance standards. Your code will be the backbone of a critical enterprise platform.
• • Engage actively in code reviews, design discussions, and iterative delivery cycles. Your input will be crucial in enhancing product velocity, code quality, and overall system robustness.
• • This role offers a significant opportunity for professional growth and continuous learning within a dynamic and forward-thinking company. You will be at the forefront of applying AI to solve complex real-world IT operations challenges.