Job
Description
We're looking for an Lead AI Engineer who thrives in fast-paced, early-stage product environments. You'll play a critical role in designing, implementing, and evolving our AI-powered infrastructure and DevOps automation platform. This includes leveraging leading LLMs like Claude or GPT to build agents for Infrastructure-as-Code (IaC), CI/CD orchestration, and Ops workflows while also enabling fine-tuned models with a focus on security, cost optimization, and reliability. This is a hands-on, cross-functional role where you will collaborate closely with backend engineers, DevOps experts, and product leadership. Responsibilities Architect and implement intelligent infrastructure agents using Claude/GPT APIs, with support for prompting, function calling, and fine-tuning. Design and develop AI-enabled workflows for provisioning (e. g., EKS, VPC, IAM), CI/CD pipelines, and operational playbooks. Build connectors to integrate LLM outputs with APIs, CLI tools, Terraform/OpenTofu providers, and observability systems. Work with vector stores (e. g., Milvus, Pinecone) and embedding pipelines to enable contextual memory and tool selection for agents. Collaborate on custom model tuning with secure guardrails and agent sandboxing mechanisms. Develop secure and modular APIs to allow frontend orchestration and runtime control of AI agents. Contribute to code reviews, shared libraries, and internal tooling to accelerate AI-driven development. Requirements 5+ years of experience in backend/AI software development with strong fundamentals in microservices and APIs. Deep experience using OpenAI/Anthropic APIs (e. g., GPT-4 Claude), prompt engineering, and advanced function calling mechanisms. Solid experience with Golang, Python, or Node.js for agent workflows, API services, or tooling. Understanding of LLM deployment strategies, prompt lifecycle, and AI-agent chaining concepts. Experience integrating with REST/gRPC APIs, message queues, and asynchronous job processing. Familiarity with vector stores (e. g., Milvus, FAISS), embeddings, and search optimization. Hands-on experience with secure AI workflows managing API tokens, prompt injection defense, and logging. Exposure to containerization (Docker), GitOps (e. g., GitHub Actions), and infrastructure systems. Nice-to-Have Familiarity with OpenTofu/Terraform, Kubernetes, and IaC principles. Experience fine-tuning models using open-source tools (e. g., LoRA, Hugging Face Transformers). Prior work on DevOps tooling, observability pipelines (OpenTelemetry, Prometheus), or infra agents. Interest in building low-code interfaces for orchestrating AI-driven infrastructure tasks. Why Join Ops0 You'll be part of a ground-floor team building a next-gen DevOps automation platform powered by AI agents. If you enjoy blending AI with infrastructure, architecting intelligent workflows, and creating real impact with hands-on ownership, this role is for you. Show more Show less
