4 days ago
Frisco, TX, USASenior
Responsibilities
- Lead the design and development of Trellix’s generative AI platform, including core functionality, agentic workflows, and platform-level features.
- Own features end to end from design and development through testing, automation, deployment, and operational health.
- Build and harden multi-agent pipelines with tool use, inter-agent coordination, and autonomous decision workflows for security operations.
- Implement resilient, secure, and performant applications handling sensitive security operations data.
- Design observability and telemetry using OpenTelemetry and contribute to operational dashboards and platform health insights.
- Produce technical designs, architectural decision records, and detailed documentation for distributed collaboration.
- Own production issue response, including triage, root-cause analysis, post-mortems, and SLA commitments.
Requirements
- 5+ years of professional experience developing Python applications and building or operating production AI or platform systems.
- Proficiency with Linux, Python development and debugging, data structures, design patterns, REST and asynchronous web APIs, and CI/CD pipelines.
- Hands-on production experience with large language models, including required LangChain experience building and operating stateful multi-agent workflows.
- Experience with prompt orchestration, chain composition, agentic AI patterns, and deploying and operating vLLM for self-hosted inference.
- Familiarity with MCP, FastAPI, Node.js/TypeScript, Postgres, knowledge graphs, vector databases, embedding pipelines, Gunicorn or Uvicorn, Redis, Kubernetes, and AWS services including RDS, EKS, ElastiCache, and Bedrock.
- Experience with Langfuse or LangSmith for agent observability is preferred.
- Working knowledge of threat detection, EDR telemetry, SOC workflows, or SIEM platforms is strongly preferred; incident response knowledge is a plus.
- Strong written and verbal communication skills, autonomy, collaboration, and the ability to explain technical decisions to non-engineering stakeholders.
Benefits
- Retirement plans, medical, dental and vision coverage, paid time off, paid parental leave, and support for community involvement.
- Flexible work hours and family-friendly benefits are provided.
- The posting does not specify a work arrangement or location.
Tech Stack
Categories
About Trellix
Trellix is a global cybersecurity company delivering intelligence-led cyber resilience for security-conscious organizations at any stage of their journey. Transforming over 30 years of threat intelligence into high-fidelity detections and automating AI-driven detection and response across cloud, on-premises, air-gapped, and operational technology environments, Trellix helps customers adapt to the constantly evolving threat landscape. More at https://trellix.com.