> Markdown version of [/jobs/ext/4617007-senior-staff-software-engineer-ai-agents](https://www.wearedevelopers.com/jobs/ext/4617007-senior-staff-software-engineer-ai-agents). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Senior / Staff Software Engineer (AI Agents)

- **Company:** ACTIVELY INC.
- **Location:** San Francisco, CA, United States
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** Automated Storage and Retrieval Systems, Data Stores, Fault Tolerance, Python (Programming Language), Performance Tuning, Data Streaming, Enterprise Software Applications, Large Language Models, Concurrency, Backend, Agentic-AI, Build Management, Apache Kafka
- **Published:** November 7, 2026
- **Apply:** https://www.juju.com/job/28_25303_9109dd461820b9f3116ab59f7fe50abf

## About the Role

* Experienced systems builder. You've designed and operated large-scale, event-driven backend systems - modeling complex, long-lived workflows into clear, maintainable, and reliable software.
 * Strong backend engineer. Deep Python expertise and solid fundamentals in concurrency, transactions, and performance tuning.
 * Architectural thinker. You reason about trade-offs between consistency, latency, fault-tolerance, and cost - building for correctness and adaptability.
 * Product-minded. You care about usability, developer experience, and how system design translates into real customer value.
 * Fluent in modern infrastructure. Familiar with streaming and workflow technologies (Kafka, Pub/Sub, Temporal-like), and data stores across relational, in-memory, and vector paradigms.
 * Collaborative and pragmatic. You value iteration, clear communication, and helping others move faster without sacrificing quality.
 * Curious about AI systems. You're excited by how LLMs, retrieval systems, and agents can transform enterprise software - and you want to build the infrastructure that makes it real., * Built or contributed to LLM-powered or agent-driven systems - such as real-time inference pipelines, context and retrieval systems, or human-in-the-loop orchestration.
 * Experience scaling mission-critical systems with high reliability requirements (payments, messaging, logistics, orchestration).
 * Comfort working in fast-moving, high-ambiguity environments where you balance big vision with tactical delivery.

## Description

We're looking for a Senior/Staff Backend Engineer to architect and build large scale systems that power Actively's GTM AI agents. These agents continuously reason over real-time customer and external data, generate next-best actions, and execute them reliably across systems with humans in the loop.

In this role, you'll design the scalable, event-driven, and fault-tolerant infrastructure that makes this intelligence possible - integrating with LLMs, orchestrating complex workflows, and ensuring every action happens with high reliability. This is a foundational role, shaping how production-grade agents operate at enterprise scale., * Design and build the agents that power Actively's platform. Model complex customer and business workflows into clear, reliable agent logic that reasons over streaming data, maintaining state, decides what to do next, and acts consistently across systems - continuously and at massive scale.

 * Develop orchestration and workflow primitives for agent and human collaboration. Translate nuanced, long-running real-world scenarios - multi-step workflows, customer-specific rules, and human-in-the-loop actions - into well-structured agent behaviors that are predictable, maintainable, and easy to extend.
 * Ensure reliability through good modeling. Design agents with clear state transitions, strong data contracts, and explicit guarantees - embedding observability and fault tolerance into their design so they behave correctly over millions of events and long-held sessions.
 * Continuously evolve agent design. Simplify complex behavior through better abstractions, documentation, and testing - ensuring agents remain reliable and comprehensible as capabilities, data volume, and concurrency grow.