Bay Area, California, US
1 day ago
Staff Software Engineer - Agentic AI Platform

Your Role:

Tenable is not only building great products and carving out a completely new category, but we are also building a world-class engineering culture committed to hiring the very best.

We are looking for a Staff Software Engineer to join a founding initiative within our engineering organization. In this role, you will help design and implement the Agentic AI Platform, the orchestration layer and nervous system that enables autonomous agents to reason, plan, and execute complex security workflows across our Exposure Management ecosystem.

This is a hands-on engineering role with broad impact. You will not just be "using" LLMs; you will be building the distributed systems, state machines, and tooling that transform generative models into reliable, enterprise-grade agents. 

While you will work from home the majority of your time, there may be an expectation to gather for in-person meetings on occasion. 

Your Opportunity:

Build the Agentic Backbone: Architect and implement the backend services that power multi-agent workflows. You will build systems that allow AI agents to decompose complex user requests, manage state, and execute tasks across distributed microservices. Orchestration & Workflow Automation: Design scalable workflow engines and "human-in-the-loop" systems. You will enable agents to perform long-running investigations and remediation tasks, balancing autonomy with control. Bridge AI & Enterprise Infrastructure: Create the integration layer between modern Python-based AI frameworks and Tenable’s robust JVM-based microservices architecture. Reliability & Guardrails: Implement verification layers, citations, and security guardrails to ensure agents operate deterministically and safely. You will treat "prompts" as code and model outputs as untrusted input that requires validation. Tooling & RAG: Build advanced Retrieval-Augmented Generation (RAG) pipelines and "Tool Use" capabilities, allowing agents to query databases, call internal APIs, and synthesize data from disparate sources. Lead Technical Direction: Collaborate with researchers and product leads to define the roadmap for AI orchestration. Champion best practices for MLOps, agent evaluation, and system observability.

What You’ll Need:

B.S. or M.S. in Computer Science, Engineering, or a related field, or equivalent practical experience. 7+ years of software engineering experience, with a strong background in building backend systems, APIs, and platforms. Agentic AI Expertise: Hands-on experience building AI agents and autonomous workflows using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or Pydantic AI. Polyglot Proficiency: Strong programming skills in Python (essential for AI/ML ecosystems) with experience in, or a willingness to work with, JVM-based languages (Java, Kotlin, or Scala) for high-scale platform components. Distributed Systems: Experience designing event-driven architectures, managing concurrency, and building fault-tolerant services (e.g., using Kafka, gRPC, REST). Data Fluency: Proficiency with Relational Databases (PostgreSQL) and experience with Vector Databases (e.g., Pinecone, Weaviate, Milvus) or search engines (Elasticsearch). Builder Mindset: A self-starter who thrives in ambiguity and is passionate about taking AI from "prototype" to "production-grade." LLM Ops & Evaluation: Experience designing frameworks to evaluate agent performance (accuracy, latency, cost) and implementing CI/CD for AI workflows. Cloud Native: Experience deploying and scaling services in AWS using Docker and Kubernetes. Graph & Search: Familiarity with Knowledge Graphs or advanced search algorithms to improve agent reasoning.

And Ideally:

LLM Ops & Evaluation: Experience designing frameworks to evaluate agent performance (accuracy, latency, cost) and implementing CI/CD for AI workflows. Cloud Native: Experience deploying and scaling services in AWS using Docker and Kubernetes. Graph & Search: Familiarity with Knowledge Graphs or advanced search algorithms to improve agent reasoning. Security Context: Understanding of cybersecurity concepts (vulnerability management, cloud security) is a plus, but not required if you are a strong systems engineer.

Applicants must be authorized to work for any employer in the U.S. We are unable to provide sponsorship for work visas of any kind at the time of hire, or at any point during employment.

#LI-LP1

Confirm your E-mail: Send Email