CommandLink

1 week ago

Staff Software Engineer, AI Investigation & Triage

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 2 hours agoStatus: Live

Job Summary

Lead the technical direction for an AI layer that reduces mean time to triage by combining LLM reasoning with graph context. Define how alerts are grouped into incidents, how confidence and priority are assigned, and how narratives are presented to SOC/NOC analysts. Own durable workflow architecture (proto-first contracts, deterministic execution, versioning) and mentor engineers across alerting, graph/topology, and analyst investigation experiences while contributing hands-on code when triage is blocked.

Location: India, Czech Republic, Poland, Chile, Colombia, Brazil

Workplace: Remote

Employment Type: Full time

Job Function: Software Engineering

Seniority: Sr. Manager level

Key Responsibilities

•Facilitate architecture decisions for how alert correlation, LLM reasoning, and graph context combine across the investigation and triage pipeline.
•Own incident grouping design, including confidence scores, priority tiers, and how likely incident narratives are inferred and presented to SOC/NOC analysts.
•Set the technical standard for collaborative investigation (comments, side-bar conversations, shared troubleshooting, and AI-initiated ticketing after triage).
•Define durable workflow architecture using proto-first contracts, deterministic execution, and strict versioning across adjacent team workflows.
•Step in on triage-latency, narrative-accuracy, or workflow-durability issues with hands-on engineering across alerting, graph-context, and analyst-workbook components, and mentor engineers across teams.

Pay and Benefits

Perks:Flexible TimeAnnual Bonus

Key Requirements

•Recognized authority in Go and Python with a track record of building production systems others rely on.
•Deep, hands-on expertise in LLM tool calling and model routing, applying LLM reasoning to real-world structured problems.
•Mastery of Temporal workflow design, including determinism, versioning, and proto-first contracts for systems others depend on.
•Experience building novel solutions combining graph-based reasoning (e.g., Memgraph) with LLM-driven decision-making.
•Hands-on experience with multi-channel real-time systems and telemetry/protocol inputs, including Kubernetes/Helm/Docker, AWS/Azure/GCP, Kafka, OpenSearch, and OpenTelemetry/syslog/network protocols.

Experience:SaaSCybersecurityReal-time systemsLLM

Skills:Architecture leadershipMentoringStakeholder communicationProblem-solvingJudgment

Tech Stack:GoPythonLLM tool callingModel routingTemporalMemgraphKubernetesHelmDockerAWSAzureGCPKafkaOpenSearchArgoSpaceliftOpenTelemetrySyslogSNMPNetFlow

Company Brief

CommandLink

Provides secure cloud, managed IT, contact center, and cybersecurity solutions tailored for enterprises and government clients, delivering mission-critical communications, infrastructure, and support services to enable secure operations and customer engagement.

Industry: Telecommunications

Website

Loading job details...

Preparing the role view and application actions.

CommandLink

1 week ago

Staff Software Engineer, AI Investigation & Triage

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 2 hours agoStatus: Live

Job Summary

Location: India, Czech Republic, Poland, Chile, Colombia, Brazil

Workplace: Remote

Employment Type: Full time

Job Function: Software Engineering

Seniority: Sr. Manager level

Key Responsibilities

•Facilitate architecture decisions for how alert correlation, LLM reasoning, and graph context combine across the investigation and triage pipeline.
•Own incident grouping design, including confidence scores, priority tiers, and how likely incident narratives are inferred and presented to SOC/NOC analysts.
•Set the technical standard for collaborative investigation (comments, side-bar conversations, shared troubleshooting, and AI-initiated ticketing after triage).
•Define durable workflow architecture using proto-first contracts, deterministic execution, and strict versioning across adjacent team workflows.
•Step in on triage-latency, narrative-accuracy, or workflow-durability issues with hands-on engineering across alerting, graph-context, and analyst-workbook components, and mentor engineers across teams.

Pay and Benefits

Perks:Flexible TimeAnnual Bonus

Key Requirements

•Recognized authority in Go and Python with a track record of building production systems others rely on.
•Deep, hands-on expertise in LLM tool calling and model routing, applying LLM reasoning to real-world structured problems.
•Mastery of Temporal workflow design, including determinism, versioning, and proto-first contracts for systems others depend on.
•Experience building novel solutions combining graph-based reasoning (e.g., Memgraph) with LLM-driven decision-making.
•Hands-on experience with multi-channel real-time systems and telemetry/protocol inputs, including Kubernetes/Helm/Docker, AWS/Azure/GCP, Kafka, OpenSearch, and OpenTelemetry/syslog/network protocols.

Experience:SaaSCybersecurityReal-time systemsLLM

Skills:Architecture leadershipMentoringStakeholder communicationProblem-solvingJudgment

Tech Stack:GoPythonLLM tool callingModel routingTemporalMemgraphKubernetesHelmDockerAWSAzureGCPKafkaOpenSearchArgoSpaceliftOpenTelemetrySyslogSNMPNetFlow

Company Brief

CommandLink

Industry: Telecommunications

Website