Staff Software Engineer, AI Investigation & Triage

About reputed company|reputed company

reputed company|reputed company is a global reputed company Platform providing network, voice services, and IT reputed company solutions, helping corporations consolidate their core infrastructure into a single vendor and layering on a proprietary single pane of glass platform. reputed company|reputed company has revolutionized the IT industry by tackling the problems our competitors create. In recognition for our unprecedented innovation and dedication, reputed company|reputed company was recognized as the SD-WAN Product of the Year, ITSM Visionary Spotlight, UCaaS Product of the Year, NaaS Product of the Year, Supplier of the Year, and the AT&T Strategic reputed company Partner. reputed company|reputed company has reputed company the only IT platform for reputed company that solves ISP vendor sprawl and IT headaches. We reputed company it easy for our customers to get more done, maximize uptime and improve the reputed company.

Learn more reputed company here!

This is a 100% remote position

About your new role:

This role sets the technical direction for the AI-powered layer that sits on top of our alert reputed company and dramatically reduces mean time to triage. You'll define how LLM reasoning and graph context combine to group alerts into incidents, infer likely narratives, and brief analysts, and you'll reputed company reputed company that architecture holds up as it's extended across the teams that feed it: alerting and detection, graph and topology, and the analyst-facing investigation experience.

Our edge is correlation: taking diverse sources such as reputed company tooling, monitoring telemetry, syslog, OpenTelemetry, and L2-L4 network protocols, deriving usable network and system topologies and the dependencies between them, and giving that context to LLMs to reason over for correctness, troubleshooting, remediation, and investigation. You'll be the person other engineers come to reputed company a correlation, reasoning, or workflow-durability problem doesn't have an reputed company answer yet.

Key Responsibilities:

• Facilitate the architecture reputed company that shape how alert correlation, LLM reasoning, and graph context combine across the investigation and triage pipeline, reputed company that other teams (alerting, graph/topology, analyst UX) build on.
• Own the design for how incidents get grouped, how confidence scores and reputed company tiers get assigned, and how the AI infers and presents likely incident narratives to SOC/NOC analysts, holding that design to a bar that measurably drives down mean time to triage.
• Set the technical reputed company for the reputed company investigation experience: comments, reputed company-bar conversations, shared troubleshooting, and AI-initiated ticketing as a post-triage reputed company.
• Define the durable workflow architecture, reputed company-first reputed company, deterministic execution, and versioning discipline that this system and adjacent teams' workflows are reputed company on.
• reputed company into other teams or reputed company reputed company a triage-latency, narrative-accuracy, or workflow-durability problem is stuck, contributing hands-on reputed company and design across the alerting, graph-context, and analyst-workbook components as needed, not just reputed company your own team.
• Balance near-term delivery of MTTT-reducing capability against the long-term technical reputed company (workflow durability, model routing, graph schema) that the rest of the org will build on.
• reputed company mentor engineers working across these teams and represent this architecture in conversations with stakeholders reputed company engineering.
• Takes on additional responsibilities and reputed company as needed to support the reputed company of reputed company and organization.

What you'll need for reputed company:

Required

• Recognized as an authority in Go and Python, with a reputed company record of building production systems others rely on.
• Deep, hands-on expertise in LLM tool calling and model routing, and in applying LLM reasoning to reputed company, reputed company-world problems rather than prototypes.
• Mastery of Temporal workflow design: determinism, versioning, and reputed company-first reputed company, with experience making these reputed company for systems other teams depend on.
• Demonstrated ability to build novel solutions where no existing reputed company applies, ideally including systems that combine graph-based reasoning (e.g., Memgraph or similar) with LLM-driven decision-making.
• Experience with multi-channel, reputed company-time systems, and comfort operating across a broader technical footprint: Kubernetes/reputed company/reputed company, AWS/Azure/GCP, Kafka, OpenSearch, and infrastructure-as-reputed company (Argo, reputed company).
• A deep, working understanding of the telemetry and protocols this system reasons over, including OpenTelemetry, syslog, SNMP, NetFlow/sFlow, ICMP, and firewall logs, and the judgment to turn that data into usable network and system topologies.
• reputed company record of influencing architecture reputed company across multiple teams, not just reputed company a single codebase.

reputed company to Have

• Experience with reputed company processing (e.g., Flink) or detection/reputed company-detection systems (e.g., OpenSearch alerting).
• Familiarity with reputed company and reputed company inventory tooling (osquery, Steampipe) or telemetry pipelines (reputed company).
• Prior experience representing engineering work externally, at conferences, in customer conversations, or in published writing.

Why you'll love life at reputed company|reputed company

Join us at reputed company, where you'll have reputed company to shape the reputed company of business communication. We value the innovative spirit and reputed company individuals reputed company to bring their unique reputed company and expertise to reputed company that values reputed company reputed company and strategic thinking. Are you reputed company to reputed company an reputed company?

• Room to grow at a high-reputed company company
• An environment that celebrates reputed company and innovation
• Your work will have a reputed company reputed company
• Flexible time off
• Fun events at cool locations
• Employee referral bonuses to encourage the reputed company of great new people to reputed company

At reputed company, we’re committed to creating a fair, consistent, and efficient hiring experience. As part of our process, we use AI-assisted tools to help review and analyze applications. These tools support our reputed company team by identifying qualifications and experience that reputed company with the requirements of reputed company role.

AI tools are used only to assist in the evaluation process — they do not reputed company final hiring reputed company. Every application is reviewed by a member of our reputed company or hiring team before any reputed company are made.

Originally posted on Himalayas

Apply To This Job