Senior Backend Engineer

Our client is building a managed healthcare model designed to provide ongoing support beyond the initial prescription process. Their approach combines proactive care with technology to help care teams support customers more consistently throughout their journey. As part of this model, the company is developing AI infrastructure that connects internal systems with language models through agents, integrations, and automation tooling. They are seeking a Senior Backend Engineer to build the backend systems and integrations that power these AI-driven workflows in production.

Responsibilities

Design, build, and maintain backend systems supporting AI-powered products and workflows; Develop integrations and connectors that allow AI agents to interact with internal and external services; Build and maintain Model Context Protocol (MCP) tools and integrations; Develop scalable REST APIs and backend services supporting automated workflows powered by language models; Design reliable integrations between AI models, internal systems, and third-party services; Work with relational and non-relational databases to support application and integration requirements; Build and maintain asynchronous processing workflows using background jobs and queue systems such as Redis Queue, SQS, or similar technologies; Design new backend capabilities rather than focusing solely on maintenance of existing systems; Build technical infrastructure that enables AI agents to securely interact with business systems and data; Integrate language models into production backend workflows; Develop and maintain MCP servers, tools, and connectors for real-world AI applications; Evaluate technical requirements for new AI agent capabilities and translate them into reliable backend implementations; Collaborate with product and technical stakeholders to define requirements and architecture; Contribute to architectural decisions for backend services, integrations, and distributed systems; Apply strong engineering practices to microservices and production backend environments; Participate in code reviews and provide thoughtful technical feedback; Help establish and maintain architecture and engineering best practices; Document technical decisions, requirements, and implementation details; Create and maintain clear technical tickets and project documentation using Linear; Support the operational health and reliability of production systems powering AI agent workflows; Diagnose and resolve production and infrastructure issues, including network errors, timeouts, and availability problems; Troubleshoot backend services and integrations when failures occur; Identify recurring reliability issues and implement sustainable improvements; Contribute to monitoring, logging, observability, and incident-response practices; Support cloud-based production infrastructure when required; Work with cloud platforms such as AWS, GCP, Cloudflare, or similar environments; Contribute to CI/CD workflows and deployment processes; Work with containers and orchestration technologies such as Docker and Kubernetes; Support infrastructure-as-code practices using tools such as Terraform, Pulumi, or similar technologies; Apply reliability engineering principles such as uptime management, incident response, SLOs, and SLIs when applicable; Work autonomously in a distributed, fully remote engineering environment; Proactively communicate progress, technical decisions, risks, and blockers; Collaborate effectively with product, engineering, and other technical stakeholders; Translate product and business requirements into practical technical solutions; Adapt to changing priorities and ambiguity within a fast-moving environment; Take ownership of technical work from requirements through production delivery and ongoing support

Requirements

6+ years of professional backend engineering experience in production environments; Strong experience designing, building, and maintaining backend services; Experience designing and integrating REST APIs; Experience working with microservices architectures and distributed systems; Experience with relational and non-relational databases; Experience with background jobs, queues, and asynchronous processing systems; Experience working independently on production-critical systems with minimal oversight; Experience working in an early-stage startup environment or having founded or co-founded a venture; Experience operating effectively in environments with ambiguity, changing priorities, and limited resources; Strong backend software engineering and system-design fundamentals; Strong understanding of REST APIs, service integrations, and distributed systems; Experience with PHP or comparable backend technologies; Experience with queue systems such as Redis Queue, SQS, or similar platforms; Hands-on experience using AI development skills, MCP servers, or related technologies in real projects; Experience or strong interest in integrating LLMs and AI models into production systems; Understanding of Model Context Protocol (MCP) and AI-agent integration patterns; Strong production troubleshooting and debugging abilities; Ability to document technical requirements, tickets, and architecture decisions clearly; Ability to work autonomously and take ownership of technical outcomes; Strong asynchronous collaboration skills in distributed engineering environments

Nice to have

Strong experience with PHP is preferred; Hands-on experience managing cloud infrastructure using AWS, GCP, Cloudflare, or similar platforms; Experience with CI/CD pipelines and automated deployment processes; Experience using Docker and containerized development or production environments; Experience with Kubernetes or comparable orchestration technologies; Experience with monitoring, logging, and observability systems; Site Reliability Engineering experience involving uptime, incident response, on-call practices, SLOs, and SLIs; Experience with infrastructure-as-code technologies such as Terraform or Pulumi; Strong understanding of production reliability for AI-powered or highly integrated systems