Software Development Engineer – Agentic AI

Trellix•Frisco, TX

About The Position

Trellix is hiring a Software Development Engineer to design, develop, and operate a production generative AI platform that supports AI capabilities across its security portfolio. The platform is intended for real-world deployment, including federal environments, and will enable autonomous SOC workflows, multi-agent orchestration, and AI integration with security products. The role involves owning features from design and implementation through testing, automation, and ongoing operations. The engineer will build and harden agent workflows, prioritize resilience, security, and performance, and implement observability and telemetry. The position also includes producing technical design documentation, supporting operational dashboards, and managing production incidents through triage, root-cause analysis, post-mortems, and SLA commitments.

Requirements

At least 5 years of professional experience in Python application software development.
Demonstrated experience building and operating production AI or platform systems.
Proficiency with Linux.
Excellent Python development and debugging skills.
Strong understanding of data structures and design patterns.
Proficiency with REST and asynchronous Web APIs.
Experience with CI/CD pipelines, such as GitHub Actions or equivalent.
Hands-on experience with large language models in production.
Experience with LangChain, including building and operating stateful multi-agent workflows.
Experience with prompt orchestration and chain composition.
Strong written communication skills for design documentation and async collaboration.
Ability to work autonomously in a fast-moving, ambiguous environment.
Excellent communication and collaboration skills across engineering, product, and security research teams.
Ability to explain technical decisions and tradeoffs clearly to non-engineering stakeholders.

Nice To Haves

Shell scripting.
Familiarity with agentic AI concepts and patterns, including ReAct, chain-of-thought, tool use, and Deep Agents.
Experience deploying and operating vLLM for self-hosted inference.
Familiarity with MCP (Model Context Protocol) for agentic tool integration.
FastAPI.
Node.js and TypeScript for tooling and API integration layers.
Postgres.
Knowledge graphs, including NebulaGraph or equivalent.
Vector databases, including Qdrant or equivalent.
Embedding pipeline experience, including chunking strategies and retrieval tuning.
Redis.
Langfuse or LangSmith for agent observability.
Kubernetes.
AWS services including RDS, EKS, ElastiCache, and Bedrock.
Working knowledge of threat detection, EDR telemetry, SOC workflows, or SIEM platforms.
Understanding of Security Incident and Event Management (SIEM) and incident response.

Responsibilities

Design and develop the generative AI platform, including core functionality, agentic workflows, and platform-level features from concept through production.
Own features and functions through design, development, rigorous testing, automation, and ongoing operational health.
Build, iterate on, and harden multi-agent pipelines involving tool use, inter-agent coordination, and autonomous decision workflows for security operations.
Deliver solutions on time, within budget, and to quality standards that meet project goals and customer commitments.
Implement practices that ensure applications are resilient, secure, and performant, especially when handling sensitive security operations data.
Implement OpenTelemetry instrumentation, contribute to operational dashboards, and provide platform health and usage insights to stakeholders.
Analyze feature requirements and produce design documentation, architectural decision records, and async-friendly technical specifications.
Own production issues through triage, root-cause analysis, post-mortems, and SLA commitments.