Zendesk

2 days ago

Staff Machine Learning Engineer

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI

Last checked: 7 hours agoStatus: Live

Job Summary

Build and scale Zendesk’s Custom Agent Service, focusing on agent execution, knowledge retrieval, and action/connector reliability. Work on the planning loop, tool dispatch, memory integration, error recovery, and production instrumentation for model training. Integrate and harden new agent architectures for real traffic, while ensuring security and compliance (PII filtering, audit logging, governance). Use Python and Kubernetes/AWS infrastructure to deliver faster, more capable agent experiences.

Location: Melbourne, New South Wales

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Improve agent execution core including planning loop, tool dispatch, memory integration, and error recovery to make agents faster, more reliable, and more capable.
•Advance knowledge retrieval pipelines (embedding, reranking, context assembly) to balance answer quality, latency, and token cost across many knowledge bases.
•Build and harden action and connector execution with retries/timeouts/schema validation and graceful degradation when connectors fail.
•Instrument production agent execution to generate trajectories and capture reward signals to support model training.
•Implement security and compliance controls including PII filtering, audit logging, action versioning, and governance within admin-configured bounds.

Key Requirements

•5+ years of backend engineering with strong Python skills, shipping production systems across large deployments.
•Experience across the agent stack: LLM APIs, prompt engineering, tool calling, memory management, and evaluation.
•Ability to handle failure cases (garbage model outputs, connector timeouts, and customer wait time).
•Ship working code, review PRs carefully, and communicate clearly about status, blockers, and risks.

Experience:5+ years

Skills:CommunicationCode reviewReliability engineeringProblem-solving

Tech Stack:PythonGoKubernetesSpinnakerAWSECSS3ElastiCachePostgresRedisKafkaBraintrustMCPRESTGRPCReActLLM APIsPrompt engineeringTool callingMemory management

Company Brief

Zendesk

Provides cloud-based customer service and engagement software, including help desk, ticketing, chat, and CRM tools that enable businesses to manage customer support, self-service, and omnichannel communication at scale.

Industry: Enterprise Software

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Established Company

Valuation: Decacorn (USD 10B+)

Funding: Private Equity Backed

Headquarters: San Francisco, United States

Founded: 2007

Glassdoor: 4.0

Website LinkedIn Glassdoor

Loading job details...

Preparing the role view and application actions.

Zendesk

2 days ago

Staff Machine Learning Engineer

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI

Last checked: 7 hours agoStatus: Live

Job Summary

Location: Melbourne, New South Wales

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Improve agent execution core including planning loop, tool dispatch, memory integration, and error recovery to make agents faster, more reliable, and more capable.
•Advance knowledge retrieval pipelines (embedding, reranking, context assembly) to balance answer quality, latency, and token cost across many knowledge bases.
•Build and harden action and connector execution with retries/timeouts/schema validation and graceful degradation when connectors fail.
•Instrument production agent execution to generate trajectories and capture reward signals to support model training.
•Implement security and compliance controls including PII filtering, audit logging, action versioning, and governance within admin-configured bounds.

Key Requirements

•5+ years of backend engineering with strong Python skills, shipping production systems across large deployments.
•Experience across the agent stack: LLM APIs, prompt engineering, tool calling, memory management, and evaluation.
•Ability to handle failure cases (garbage model outputs, connector timeouts, and customer wait time).
•Ship working code, review PRs carefully, and communicate clearly about status, blockers, and risks.

Experience:5+ years

Skills:CommunicationCode reviewReliability engineeringProblem-solving

Tech Stack:PythonGoKubernetesSpinnakerAWSECSS3ElastiCachePostgresRedisKafkaBraintrustMCPRESTGRPCReActLLM APIsPrompt engineeringTool callingMemory management

Company Brief

Zendesk

Industry: Enterprise Software

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Established Company

Valuation: Decacorn (USD 10B+)

Funding: Private Equity Backed

Headquarters: San Francisco, United States

Founded: 2007

Glassdoor: 4.0

Website LinkedIn Glassdoor