Claude prompts for MLOps and ML platform engineer job searches

I am applying for the MLOps / ML platform engineer role below. Rewrite my resume to match it using only experience that is already on my resume. Do not invent tools, scale numbers, uptime figures or systems I have not run. The posting may ask for orchestration, feature stores, model registries, CI/CD for models, serving, monitoring, cloud platforms or Kubernetes; for each requirement, find the closest real evidence in my resume, and if there is none, put it under "Gaps" rather than writing it in. Output: a table with the columns requirement, evidence, rewritten bullet; a revised one-page resume in plain text where each bullet names the system, what I did to it and the measured effect (reliability, latency, cost or time saved); and the Gaps list with one honest sentence per gap. Keep every job, title and date unchanged.

Job description:
[paste job description]

My resume:
[paste your resume]

Write a cover note of at most 120 words for the MLOps / ML platform engineer role below. Use only facts from my resume and my notes. No invented results, no "passionate", no "best practices". Structure: one sentence that shows I understand the platform problem this team has (scale, reliability, the number of models or teams they serve; take it from the job description), two sentences on the most relevant system I have built or run and what it changed, with a number if I have one, and one closing sentence with a specific ask. Then give a 50-word version for a LinkedIn message. Sentence case, plain words, no exclamation marks.

Job description:
[paste job description]

My resume:
[paste your resume]

Why this team, in my words:
[two or three lines]

Act as the interviewer for a 45-minute MLOps / ML platform engineer technical screen at the company below. Ask one question at a time and wait for my answer. Cover, in order: one coding question in Python or a shell (for example parsing logs, writing a retry with backoff, or a small script that validates a model artifact), two infrastructure questions drawn from the job description (for example how to version data and models, what belongs in a training pipeline versus a serving pipeline, how to roll out a new model safely, what to monitor for drift, or containers and resource limits), one question about a system on my resume, and one debugging scenario (a model endpoint is slow after a deploy; where do you look first). After each answer, score it 1 to 5, give a strong answer, and name the one thing I should have said. End with three topics to review tonight.

Job description:
[paste job description]

My resume:
[paste your resume]

Run an ML platform design interview with me for the role below. Pick a problem that fits the company (for example a training and deployment platform for twenty teams, a feature store, a real-time inference service with strict latency, or batch scoring for millions of rows nightly) and describe it in two sentences. Guide me one stage at a time, waiting for my answer: requirements and who the users are, data and feature pipelines, experiment tracking and the model registry, CI/CD for models including tests, serving architecture and scaling, rollout strategy (shadow, canary, A/B), monitoring for both system and model health, retraining triggers, cost controls, and access and audit. After each stage, point out what an experienced platform engineer would have raised that I missed. Finish with a one-page summary in my corrected words. Do not give the full answer up front.

Job description:
[paste job description]

What I know about the product:
[a few lines]

Help me prepare behavioral answers for an MLOps / ML platform engineer interview using only the situations I describe below. Do not add details; if a story is missing an outcome or a number, ask me for it. First list the eight questions most likely for this role and company (an incident you handled, a migration that went wrong, convincing data scientists to adopt a platform, a disagreement about tooling, a cost problem, a mistake you owned, balancing reliability against speed, and supporting a team under pressure). Then map each to one of my stories and write an answer of 150 to 200 words in the shape situation, action, result, what I would do differently. Flag where the same story is used twice so I can spread them out.

Job description:
[paste job description]

My stories, rough notes are fine:
[three to five real situations]

Turn my notes below into a portfolio write-up of 500 to 700 words about a platform or infrastructure project, first person, plain language, aimed at a hiring manager. Use only what is in my notes. Where something important is missing (the scale, the number of users or models, the before and after numbers for reliability, latency, cost or time, the tools, what broke), insert a placeholder in square brackets and list the placeholders at the end. Structure: the problem and who it hurt, the constraints, the design and the alternative I rejected and why, how I rolled it out, the measured effect, what went wrong or what I would change, and what came next. Suggest a title, a two-sentence README summary, three honest resume bullets, and one architecture diagram I should draw with its boxes named.

Project notes:
[paste notes, design docs, postmortems or a rough description]

I have an offer for an MLOps / ML platform engineer role. Below are the offer details, my current compensation, any competing offers and what I have found from public sources. Help me evaluate and negotiate honestly; do not invent market data, and tell me what to look up if you need a number I have not given. Output: (1) a table of four-year total compensation under a cautious and an optimistic equity assumption; (2) which components are most negotiable for this kind of company and why; (3) a short script for the call that asks for a specific number with a reason tied to my experience, in a collaborative tone; (4) questions to ask before accepting, including the level, vesting, the on-call rotation and how it is compensated, the team's ownership boundaries, the state of the current platform, and how success is measured. Under 500 words.

Offer:
[base, bonus, equity and vesting, signing bonus, location]

My situation:
[current compensation, competing offers, constraints]

Write a 30/60/90-day plan for me as a new MLOps / ML platform engineer on the team below. Keep it realistic: I have to learn the existing platform, the on-call process, the users and their pain before changing anything. Days 1 to 30: which pipelines and services exist, how deploys happen today, what the incident history says, and what the data scientists complain about most. Days 31 to 60: a first contribution, for example a flaky pipeline stabilized, a missing alert added, a deploy step automated, or a cost saving measured. Days 61 to 90: a measurable project with a success metric and risks. For each block, give three to five outcomes rather than activities and one question to ask my manager in week one. Mark assumptions I should verify. Under 450 words.

Job description:
[paste job description]

What I learned about the team in interviews:
[notes]

Audit the ML deployment pipeline described below as a senior platform engineer would, so I can present the findings in a take-home or design round. Be direct and specific. Check for: reproducibility (pinned dependencies, data and model versioning, seeds), testing (unit tests for feature code, a model quality gate before deploy, a schema check on inputs), rollout safety (canary or shadow, a rollback path, who approves), observability (latency, error rate, prediction distribution, data drift, alerting and who gets paged), security (secrets handling, access to data and models, an audit log), and cost (idle resources, batch versus real-time choices). Output: a table of findings with severity, the evidence, and a fix in one or two sentences each; the three changes I would make first and why; and a short paragraph I could say out loud that summarizes the state of the pipeline honestly without overclaiming what I could see.

The pipeline, as code, a diagram or a description:
[paste it]