Home › Companies › C Serv › Adversarial Machine Learning Engineer
Adversarial Machine Learning Engineer
C Serv · Vancouver, Canada (Hybrid) · Hybrid · Deleted · Workable
Job facts
| Field | Value |
|---|---|
| Company | C Serv |
| Title | Adversarial Machine Learning Engineer |
| Normalized title | - |
| Department / team | Other |
| Location | Vancouver, Canada |
| Work model | Hybrid / Hybrid |
| Employment type | - |
| Salary | - |
| Status | deleted |
| ATS provider | Workable |
| Posted / first seen | 2026-05-18 / 2026-05-31 |
| Changed / last seen | 2026-06-03 / 2026-06-01 |
Related slices
| Page | What it contains | Open |
|---|---|---|
| Company jobs | Active postings from C Serv. | Open |
| Company breakdowns | Role, location, ATS, and work model facets for this company. | Open |
| ATS provider jobs | Active postings observed through Workable. | Open |
| Provider filtered search | The same provider as a filtered job collection. | Open |
| City jobs | Active postings in Vancouver. | Open |
| Department jobs | Active postings in Other. | Open |
| Work model jobs | Active Hybrid postings. | Open |
| Lifecycle events | Open, update, close, and reopen events for this posting. | Open |
| Original posting | Canonical source or apply URL captured from the ATS. | Open |
Linked records
| Company | C Serv |
| Source | d7624994-1633-467b-883c-404e80e852c0 |
| ATS provider | Workable |
Description
Description
The Opportunity
We are building a dedicated AI Red Team to rigorously test and harden enterprise scale AI products.
We are looking for an adversarial machine learning specialist who thinks like an attacker.
This role focuses on identifying vulnerabilities in LLM driven systems, breaking model guardrails, exploiting data pathways, and stress testing AI deployments before they reach enterprise customers.
This is a hands on technical role at the core of AI security.
What You’ll Do
Conduct adversarial testing across LLM and AI based systems
Execute real world attack simulations, including:
Prompt injection
Jailbreaking and guardrail bypass
Data exfiltration attempts
Model inversion and evasion techniques
RAG manipulation
Develop scripts and tooling to automate attack scenarios
Analyse model behaviour under adversarial pressure
Identify systemic vulnerabilities in:
APIs
Embedding pipelines
Vector databases
Fine tuned model implementations
Collaborate with engineering teams to validate remediation
Document findings clearly and concisely
You will help ensure AI systems are resilient before they are deployed at scale.
Requirements
What We’re Looking For
Core Technical Skills
Strong experience in adversarial ML or AI security research
Experience working with LLM based systems (OpenAI, Anthropic, open source models, etc.)
Deep understanding of:
Prompt injection techniques
Model jailbreak methodologies
AI system exploitation vectors
Strong Python skills
Experience building custom attack tooling or experimentation frameworks
AI Systems Knowledge
Familiarity with:
RAG architectures
Vector databases
Model fine tuning workflows
API based model deployments
Understanding of model safety mechanisms and guardrails
Nice to Have
Background in cybersecurity or penetration testing
Familiarity with OWASP LLM Top 10
Experience working in enterprise environments
Who You Are
Curious and relentless
Comfortable thinking like an attacker
Creative in finding non obvious vulnerabilities
Detail oriented but fast moving
Comfortable operating in ambiguity
Independent but collaborative
You don’t just run test cases — you design new ones.
Benefits
Comprehensive Private Medical Coverage
Support for Mental Health Expenses
Life Insurance Options
Attractive Compensation Package
Full job record
| Job ID | 0f2191f498df7c9d476969ceac58cb95f5b4f62c |
| Org ID | 7b906b24-5234-4df3-a384-1fe53b3bf301 |
| Source ID | d7624994-1633-467b-883c-404e80e852c0 |
| Board ID | d7624994-1633-467b-883c-404e80e852c0 |
| Provider | workable |
| Provider Job Key | EE4451AE3D |
| Title | Adversarial Machine Learning Engineer |
| Normalized Title | — |
| Status | deleted |
| Active | no |
| Location Text | Vancouver, Canada (Hybrid) |
| Department | Other |
| Team | — |
| Employment Type | — |
| Workplace Type | hybrid |
| Remote Policy | hybrid |
| Country | Canada |
| Region | — |
| City | Vancouver |
| Salary Raw | Description The Opportunity We are building a dedicated AI Red Team to rigorously test and harden enterprise scale AI products. We are looking for an adversarial machine learning specialist who thinks like an attacker. This role focuses on identifying vulnerabilities in LLM driven systems, breaking model guardrails, exploiting data pathways, and stress testing AI deployments before they reach enterprise customers. This is a hands on technical role at the core of AI security. What You’ll Do Conduct adversarial testing across LLM and AI based systems Execute real world attack simulations, including: Prompt injection Jailbreaking and guardrail bypass Data exfiltration attempts Model inversion and evasion techniques RAG manipulation Develop scripts and tooling to automate attack scenarios Analyse model behaviour under adversarial pressure Identify systemic vulnerabilities in: APIs Embedding pipelines Vector databases Fine tuned model implementations Collaborate with engineering teams to validate remediation Document findings clearly and concisely You will help ensure AI systems are resilient before they are deployed at scale. Requirements What We’re Looking For Core Technical Skills Strong experience in adversarial ML or AI security research Experience working with LLM based systems (OpenAI, Anthropic, open source models, etc.) Deep understanding of: Prompt injection techniques Model jailbreak methodologies AI system exploitation vectors Strong Python skills Experience building custom attack tooling or experimentation frameworks AI Systems Knowledge Familiarity with: RAG architectures Vector databases Model fine tuning workflows API based model deployments Understanding of model safety mechanisms and guardrails Nice to Have Background in cybersecurity or penetration testing Familiarity with OWASP LLM Top 10 Experience working in enterprise environments Who You Are Curious and relentless Comfortable thinking like an attacker Creative in finding non obvious vulnerabilities Detail oriented but fast moving Comfortable operating in ambiguity Independent but collaborative You don’t just run test cases — you design new ones. Benefits Comprehensive Private Medical Coverage Support for Mental Health Expenses Life Insurance Options Attractive Compensation Package |
| Salary Min | — |
| Salary Max | — |
| Salary Currency | — |
| Salary Period | — |
| Source URL | https://apply.workable.com/c-serv/jobs/view/EE4451AE3D |
| Apply URL | https://apply.workable.com/c-serv/j/EE4451AE3D/apply |
| First Seen At | 2026-05-31 17:47:36Z |
| Last Seen At | 2026-06-01 12:11:06Z |
| Last Checked At | 2026-06-03 12:31:19Z |
| Last Changed At | 2026-06-03 12:31:19Z |
| Inactive At | 2026-06-03 12:31:19Z |
| Source Posted At | 2026-05-18 00:00:00Z |
| Source Updated At | — |
| Raw Payload Uri | s3://bluework-jobs-prod-raw-590183727216/raw/provider=workable/board=c-serv/date=2026-06-01/2026-06-01T12-11-06-220Z-eb24c18061a3098694b81344d361fc445d93384308e4622ce5fa70c069948a97.json |
Event Fields
{
"content_hash": "b2054cc4696ef7f3adc3fe34626a70311973f9aa595f4f0a9e2bb639a5262492",
"source_hash": "ef91ab0025c8c382046e361b65c6e3bfb96f6d3120e8596c0f8249488ec13098",
"last_changed_at": "2026-06-03T12:31:19.530Z",
"active_status": "deleted"
}Parsed Structured
{
"language": "en",
"location": {
"raw": "Vancouver, Canada (Hybrid)",
"city": "Vancouver",
"region": null,
"country": "Canada",
"is_remote": false,
"confidence": 0.95
},
"salary_max": null,
"salary_min": null,
"inferred_at": "2026-06-01T12:11:06.792Z",
"launch_scope": {
"reason": "english_us_canada",
"included": true,
"language": "en",
"location": {
"raw": "Vancouver, Canada (Hybrid)",
"city": "Vancouver",
"region": null,
"country": "Canada",
"is_remote": false,
"confidence": 0.95
},
"countries": [
"Canada"
]
},
"remote_policy": "hybrid",
"salary_period": null,
"workplace_type": "hybrid",
"salary_currency": null
}Extensions
{}Native Structured
{
"detail": {
"type": "—",
"title": "Adversarial Machine Learning Engineer",
"posted": "2026-05-18",
"company": "C-Serv",
"applyUrl": "https://apply.workable.com/c-serv/j/EE4451AE3D/apply",
"location": "Vancouver, Canada (Hybrid)",
"workplace": "hybrid",
"department": null,
"descriptionText": "Description\n\n The Opportunity\n\nWe are building a dedicated AI Red Team to rigorously test and harden enterprise scale AI products.\n\nWe are looking for an adversarial machine learning specialist who thinks like an attacker.\n\nThis role focuses on identifying vulnerabilities in LLM driven systems, breaking model guardrails, exploiting data pathways, and stress testing AI deployments before they reach enterprise customers.\n\nThis is a hands on technical role at the core of AI security.\n\n What You’ll Do\n\n Conduct adversarial testing across LLM and AI based systems\n Execute real world attack simulations, including:\n Prompt injection\n Jailbreaking and guardrail bypass\n Data exfiltration attempts\n Model inversion and evasion techniques\n RAG manipulation\n Develop scripts and tooling to automate attack scenarios\n Analyse model behaviour under adversarial pressure\n Identify systemic vulnerabilities in:\n APIs\n Embedding pipelines\n Vector databases\n Fine tuned model implementations\n Collaborate with engineering teams to validate remediation\n Document findings clearly and concisely\n\nYou will help ensure AI systems are resilient before they are deployed at scale.\n\n Requirements\n\n What We’re Looking For\n\n Core Technical Skills\n\n Strong experience in adversarial ML or AI security research\n Experience working with LLM based systems (OpenAI, Anthropic, open source models, etc.)\n Deep understanding of:\n Prompt injection techniques\n Model jailbreak methodologies\n AI system exploitation vectors\n Strong Python skills\n Experience building custom attack tooling or experimentation frameworks\n\n AI Systems Knowledge\n\n Familiarity with:\n\n RAG architectures\n Vector databases\n Model fine tuning workflows\n API based model deployments\n Understanding of model safety mechanisms and guardrails\n\n Nice to Have\n\n Background in cybersecurity or penetration testing\n Familiarity with OWASP LLM Top 10\n Experience working in enterprise environments\n\n Who You Are\n\n Curious and relentless\n Comfortable thinking like an attacker\n Creative in finding non obvious vulnerabilities\n Detail oriented but fast moving\n Comfortable operating in ambiguity\n Independent but collaborative\n\nYou don’t just run test cases — you design new ones.\n\n Benefits\n\n Comprehensive Private Medical Coverage\n Support for Mental Health Expenses\n Life Insurance Options\n Attractive Compensation Package"
},
"list_job": {
"id": "EE4451AE3D",
"type": null,
"title": "Adversarial Machine Learning Engineer",
"posted": "2026-05-18",
"salary": null,
"location": "Vancouver, Canada (Hybrid)",
"detailUrl": "https://apply.workable.com/c-serv/jobs/view/EE4451AE3D.md",
"department": "Other"
},
"detail_meta": {
"url": "https://apply.workable.com/c-serv/jobs/view/EE4451AE3D.md",
"http_status": 200,
"content_type": "text/markdown; charset=utf-8",
"response_bytes": 2797
},
"detail_errors": []
}Get this page with API
Rendered from the bluedoor Job Postings API. Reproduce it:
GET https://api.bluedoor.sh/job-postings/v1/jobs/0f2191f498df7c9d476969ceac58cb95f5b4f62c?include=descriptionJSONGET https://api.bluedoor.sh/job-postings/v1/orgs/7b906b24-5234-4df3-a384-1fe53b3bf301JSONGET https://api.bluedoor.sh/job-postings/v1/sources/d7624994-1633-467b-883c-404e80e852c0JSONGET https://api.bluedoor.sh/job-postings/v1/jobs/0f2191f498df7c9d476969ceac58cb95f5b4f62c/eventsJSON