Note: The job is a remote job and is open to candidates in USA. TubeScience builds software systems that combine AI, engineering, and automation to solve complex operational problems at scale. The Senior Applied AI Engineer will design, implement, and operate AI-powered enterprise systems that automate business processes, working directly with internal stakeholders to identify and solve operational challenges.
Responsibilities
- Design and build production AI applications that automate complex enterprise workflows
- Architect agent-based systems that coordinate LLMs, APIs, internal services, databases, and business logic
- Build reliable orchestration layers that integrate multiple tools and enterprise platforms
- Deploy production-ready AI systems with observability, monitoring, rollback strategies, and operational safeguards
- Investigate production issues, analyze logs, debug failures, and restore system reliability when incidents occur
- Design scalable architectures that prioritize maintainability, resiliency, and operational excellence
- Partner closely with Product, Operations, Creative, Engineering, and Business teams to identify high-impact automation opportunities
- Rapidly prototype, validate, deploy, and iterate solutions based on production performance and business outcomes
- Continuously improve existing AI systems for reliability, speed, and business impact
Skills
- 3–6+ years of professional software or systems engineering experience
- Experience building and operating production software used by real users or internal business teams
- Strong Python engineering experience
- Experience integrating modern LLMs into production systems using frameworks such as OpenAI, Anthropic, LangGraph, MCP, or similar
- Experience designing systems that coordinate multiple APIs, databases, services, and enterprise applications
- Strong understanding of distributed systems, debugging, logging, monitoring, and production operations
- Experience deploying, operating, troubleshooting, and improving production systems after launch
- Strong architectural thinking with the ability to design complete end-to-end solutions
- Comfort working independently in a fast-paced startup environment
- Experience at a large technology company building production systems
- Experience with multi-agent systems
- Experience with LangGraph, MCP, Temporal, or similar orchestration frameworks
- Experience with event-driven architectures
- Experience with Docker and Kubernetes
- Experience with AWS, GCP, or Azure
- Experience with CI/CD pipelines
- Experience with observability platforms (Datadog, Grafana, OpenTelemetry, etc.)
- Experience with internal developer platforms
- Experience with enterprise integrations
Company Overview
Company H1B Sponsorship