Senior AI Software Engineer, Python

The Senior AI Software Engineer, Python will be responsible for making Scorpion’s Conversational Intelligence Platform production-grade by building reliable, observable, and scalable infrastructure for real-time AI workloads, including LLM orchestration, streaming responses, and event-driven messaging across multiple communication channels.

This role owns the runtime reliability of systems that process LLM inference pipelines, manage backpressure across async workloads, and maintain clean service boundaries with downstream teams. Operating within an established architecture, the Senior AI Software Engineer, Python is responsible for the operational excellence required to make the platform production-ready.

• →Own the reliability of the event-driven messaging layer, including backpressure management, idempotency, dead-letter handling, and retry strategies.
• →Build and operate the infrastructure that runs LLM orchestration workloads at scale.
• →Own the operational data layer for the CI runtime, including state management, session persistence, and real-time data access patterns.
• →Own observability for the CI platform, including structured logging, distributed tracing (OpenTelemetry), and error tracking (Sentry).
• →Maintain and harden the interfaces between CI and downstream platforms, including contract testing, versioning, and failure handling.
• →Conduct code reviews and mentor team members on Python engineering practices and production readiness.
• →Own production support for CI infrastructure, including on-call responsibilities and incident response.

• Experience
  • 5+ Years of Experience or Relevant Experience.
  • Developing production-grade Python services at scale.
  • Operating real-time or high-throughput infrastructure supporting AI/ML workloads.
  • Designing and operating distributed, event-driven systems in production environments.

• Hard / Technical Skills
  • Deep command of Python internals: async/await lifecycle, event loop mechanics, GIL implications for concurrency strategy, memory profiling.
  • Production experience with Pydantic, type systems, and structured data modeling in high-throughput services.
  • Strong opinions on code organization, error handling patterns, and testability in long-lived Python codebases.
  • Hands-on experience operating LLM inference infrastructure at scale.
  • Deep experience with NoSQL data modeling: partition strategy, consistency tradeoffs, query cost optimization, and hot-partition avoidance.
  • Experience with event-driven architecture in production: backpressure, idempotency, dead-letter handling, retry strategies.
  • Proficiency with observability tooling: distributed tracing (OpenTelemetry), structured logging, error tracking (Sentry).
  • Experience with Azure cloud platform services.

• Professional / Core Skills
  • Ability to negotiate technical boundaries with teams that own upstream and downstream services.
  • Clear, direct communication in design discussions, incident response, and code review.

• Winning Mindset: When our clients win, we win.
• Genuine Care: We only succeed when we are truly invested in our clients and each other.
• Unmatched Results: We deliver more than expected–and then some–driving the best results and impacting lives.
• Constant Improvement: We believe there is always a better way. We learn we ask “What if?” we build and then do it again.
• Unbeatable Teamwork: We come from different backgrounds but have the same vision. We only get there by doing it together, as a team.

Scorpion supports a range of work arrangements, including in-office, hybrid, and remote roles. For positions designated as remote, employees who live within commuting distance of a Scorpion office may be asked to work from the office based on team needs, collaboration opportunities, or business priorities. Specific expectations will be discussed during the interview process.