Sr. Python Engineer, Agentic AI

Comcast•Washington, DC

1d•Hybrid

About The Position

We are looking for a Senior Software Engineer to lead the technical direction of our AI Agent initiatives. This is a backend engineering role first, focused on building scalable, reliable systems that happen to use modern AI techniques. You will architect and operate production‑grade backend services and agentic workflows that solve complex, non‑deterministic problems. While LLMs are a core capability, success in this role comes from strong systems thinking, designing for correctness, observability, failure recovery, and long‑term maintainability. You will serve as a technical anchor for the team—mentoring junior engineers, setting engineering standards, and working with leadership to turn AI concepts into dependable, customer‑facing systems. -level machine learning expertise and innovation capacity are essential.

Requirements

Extensive experience designing, building, and operating backend systems in Python, including asynchronous frameworks (FastAPI, asyncio) and distributed service architectures.
A track record of owning customer‑facing systems in production. You understand uptime, latency budgets, incident response, and the cost of unreliable behavior.
Hands‑on experience integrating LLMs into real systems, with a clear understanding of their limitations, failure modes, and operational risks. You think in terms of workflows, control flow, and safeguards—not just prompt quality.
Experience building AI agents that interact with tools, APIs, and external systems, including managing agent state, bounding autonomy, and preventing pathological behaviors (loops, hallucinations, cascading failures).
Comfortable being responsible for systems after launch. You design software that is “easy to wake up to” when something goes wrong.
Experience with microservices, data stores, queues, and high‑throughput APIs—and the judgment to keep designs as simple as possible.
A desire to raise the bar for those around you through feedback, example, and thoughtful technical leadership.
You enjoy leveraging advanced AI capabilities, but you prioritize stability, debuggability, and long‑term maintainability over novelty.
Adaptability
Critical Thinking
Curious Mindset
Customer-Oriented
Python (Programming Language)

Responsibilities

Design and own scalable backend architectures and complex agent‑driven workflows. This includes service boundaries, data flows, failure handling, observability, and performance characteristics—not just model interaction.
Design and productionize agent behaviors including tool invocation, state management, memory strategies, and reasoning control. Prompts are treated as code: versioned, tested, reviewed, and evolved alongside backend logic for reliability, cost, and latency.
Set the bar for clean, readable, maintainable code across the Python backend. Establish patterns and standards that allow AI‑heavy systems to remain understandable and operable over time.
Design testing strategies for non‑deterministic AI components, including behavioral regression testing, automated evaluations, and guardrails that reduce blast radius in production.
Lead code reviews as a teaching tool, run architectural discussions, and actively mentor Engineer 1–2 developers in backend fundamentals, system design, and operational thinking.
Own CI/CD, deployment, and runtime health. Lead production support efforts and help build a strong on‑call culture where systems are observable, diagnosable, and resilient under real‑world load.
Partner with product and design to deliver high‑traffic, customer‑facing experiences where AI responses must meet clear standards for latency, reliability, and UX—not just correctness.
Translate product goals into pragmatic technical roadmaps, identifying scaling risks, technical debt, and AI‑specific failure modes early.
Lead investigations into complex issues spanning multiple services, data pipelines, or emergent agent behaviors in production.