senior-ml-engineer
Deploy Production ML Systems
Production ML work requires deployment, monitoring, and LLM integration across many tools. This skill provides templates and guidance for MLOps, model serving, RAG, and model monitoring.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "senior-ml-engineer" from https://skillstore.io/skills/alirezarezvani-senior-ml-engineer.md and its manifest at https://skillstore.io/api/skills/alirezarezvani-senior-ml-engineer/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "senior-ml-engineer". Plan deployment for a classification model with low latency requirements.
Expected outcome:
- Recommended serving architecture with containerized inference and autoscaling.
- Latency and throughput targets mapped to monitoring metrics.
- Release plan with canary rollout, rollback triggers, and health checks.
- Security checklist for secrets, access control, and encrypted data paths.
Using "senior-ml-engineer". Design a RAG system for internal policy documents with citations.
Expected outcome:
- Document ingestion plan with chunking, metadata, and access filters.
- Retrieval design using vector search, keyword matching, and re-ranking.
- Answer quality checks with citation coverage and confidence review.
- Operations plan for indexing updates, monitoring, and cost tracking.
Using "senior-ml-engineer". Assess whether our model monitoring is production ready.
Expected outcome:
- Gap analysis across drift, data quality, latency, errors, and business metrics.
- Alert policy with severity levels and owner routing.
- Retraining and rollback criteria linked to measurable thresholds.
Security Audit
High RiskAll static findings are false positives caused by Markdown code fences, inline file references, and ordinary RAG search wording. A separate semantic issue was found: marketplace_content.json includes self-authored security audit claims that could influence review behavior if treated as authoritative.
Confirmed security concerns (1)
Risk Factors
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/alirezarezvani-senior-ml-engineer/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/alirezarezvani-senior-ml-engineer?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/alirezarezvani-senior-ml-engineer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/alirezarezvani-senior-ml-engineer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/alirezarezvani-senior-ml-engineer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
alirezarezvani. (2026). senior-ml-engineer security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/alirezarezvani-senior-ml-engineer/audits/6BibTeX citation
@techreport{alirezarezvani-alirezarezvani-senior-ml-engineer-2026,
author = {alirezarezvani},
title = {senior-ml-engineer security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/alirezarezvani-senior-ml-engineer/audits/6},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "senior-ml-engineer security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
- name: "alirezarezvani"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/alirezarezvani-senior-ml-engineer/audits/6"
identifiers:
- type: other
value: "skillstore:alirezarezvani-senior-ml-engineer:audit:6"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
davila7-senior-ml-engineer
2026-08-21
alirezarezvani-senior-ml-engineer
2026-08-21
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Prepare a model deployment plan
Design serving, scaling, monitoring, and rollback steps for a trained model.
Convert a prototype into an MLOps workflow
Map notebooks, models, and evaluation outputs into versioned production processes.
Review RAG and LLM architecture
Assess retrieval, caching, observability, access control, and deployment patterns.
Try These Prompts
Help me plan deployment for a trained model. Ask for the model type, traffic target, latency target, cloud environment, and monitoring needs.
Design a monitoring plan for a production ML model. Include latency, errors, drift, data quality, alert thresholds, and rollback signals.
Design a RAG system for internal documents. Cover chunking, embeddings, vector storage, hybrid search, citations, evaluation, and access control.
Review our ML platform architecture for production readiness. Focus on CI, model registry, feature stores, deployment safety, observability, cost, and security.
Best Practices
- Define latency, reliability, and quality targets before choosing deployment tools.
- Track model versions, data versions, and feature definitions through the full lifecycle.
- Add monitoring for drift, data quality, service health, and business impact.
Avoid
- Deploying a model without rollback, ownership, or incident response steps.
- Treating offline validation metrics as enough evidence for production readiness.
- Building RAG pipelines without citation checks, access controls, or retrieval evaluation.
Frequently Asked Questions
Does this skill train models?
Which frameworks are referenced?
Can it deploy directly to my cloud account?
What makes it useful for RAG systems?
Is it suitable for regulated data?
Does it work with Claude, Codex, and Claude Code?
Developer Details
Author
alirezarezvaniLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Repository
https://github.com/alirezarezvani/claude-skills/tree/main/engineering-team/senior-ml-engineerRef
c4231f0153ccd2a2ed62274c5a372bf8f2386d3f
Maintenance freshness
7/18/2026
Usage
20 downloads · 228 views