Claude prompts for machine learning engineer job searches

I am applying for a machine learning engineer role. Below are the job description and my current resume. Rewrite my resume bullets so they map to what this job asks for, using only experience that is already on my resume. Do not invent projects, tools, metrics or responsibilities; if the job asks for something I have not done, list it separately under "Gaps" instead of writing it in. Keep the same jobs, titles and dates. Output: (1) a table with three columns: job requirement, matching evidence from my resume, and the rewritten bullet; (2) a revised resume in plain text, one page, with bullets that lead with the action and end with a measurable result where my resume already gives one; (3) the Gaps list with one sentence on how I could honestly address each in an interview.

Job description:
[paste job description]

My resume:
[paste your resume]

Write a cover note of at most 120 words for the machine learning engineer role below. Base it only on the facts in my resume and the notes I give you; do not add achievements, and do not use phrases like "passionate" or "perfect fit". Structure: one sentence on why this specific team or product (use a detail from the job description), two sentences on the most relevant thing I have shipped and what it did in numbers if my resume has them, and one closing sentence with a clear ask. Give me two versions: one for an application form, and one as a LinkedIn message of at most 60 words. Plain language, sentence case, no exclamation marks.

Job description:
[paste job description]

My resume:
[paste your resume]

Why I am interested, in my own words:
[two or three lines]

Act as the interviewer for a 45-minute machine learning engineer technical screen at the company below. Ask me one question at a time and wait for my answer before continuing. Cover, in order: one coding question in Python that touches data manipulation (arrays, dictionaries or pandas), two ML fundamentals questions drawn from the skills in the job description (for example bias versus variance, regularization, evaluation metrics for imbalanced data, or how gradient descent variants differ), and one short question about a model I list on my resume. After each answer, grade it from 1 to 5, state what a strong answer contains, and tell me the one thing I should have said. At the end, give me the three topics I should study tonight, with one concrete resource type for each.

Job description:
[paste job description]

My resume:
[paste your resume]

Run an ML system design interview with me for the role below. Pick a problem that fits the company's product (for example ranking, recommendations, fraud detection or demand forecasting) and state it in two sentences. Then guide me through it one stage at a time, asking a question and waiting for my answer: clarifying requirements and constraints, framing the ML problem and choosing the objective, data sources and labeling, features and feature freshness, model choice and why, offline evaluation, online evaluation and A/B testing, serving latency and cost, monitoring and retraining. After each stage, point out what an experienced engineer would have mentioned that I missed. Finish with a one-page summary of the design in my words, corrected, that I can review before the interview. Do not give me the full answer up front.

Job description:
[paste job description]

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

Help me prepare behavioral interview answers for a machine learning engineer role using only the experiences I describe below. Do not invent details; where a story is missing a specific number or outcome, ask me for it instead of filling it in. First, list the eight behavioral questions most likely for this role and company (conflict with a stakeholder, a model that failed in production, a deadline trade-off, disagreeing with a decision, mentoring, ambiguity, a mistake you owned, influencing without authority). Then, for each question, map it to one of my stories and draft an answer of 150 to 200 words in the shape situation, action, result, what I would do differently. Flag any answer that leans on a story I have already used for another question so I can spread them out.

Job description:
[paste job description]

My stories, rough notes are fine:
[describe three to five real situations with what happened and what you did]

Turn my project notes below into a portfolio write-up of 500 to 700 words for a machine learning engineer audience, written in the first person and in plain language. Use only what is in my notes; if something important is missing (dataset size, baseline, final metric, latency, what did not work), put a placeholder in square brackets and list the placeholders at the end so I can fill them. Structure: the problem and why it mattered, the data and its problems, the approach and the alternatives I rejected and why, the results against a baseline, what went wrong along the way, and what I would do next. Add a suggested title, a two-sentence summary for the top of a README, and three bullet points I could put on my resume for this project.

Project notes:
[paste your notes, commit messages or a rough description]

I have an offer for a machine learning engineer role and I want to evaluate it and negotiate honestly. Below are the offer details, my current compensation, any competing offers, and what I know about the market from public sources. Do not invent salary data; where you would need a number I have not given, tell me what to look up instead. Output: (1) the total compensation over four years under a conservative and an optimistic assumption for equity, shown as a table; (2) the three components most worth negotiating for this kind of offer and why; (3) a short script for the call, in plain sentences, that asks for a specific number and gives a reason tied to my experience; (4) the questions I should ask before accepting (vesting schedule, refresh policy, on-call, team scope, remote policy). Keep the tone collaborative.

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

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

Draft a 30/60/90-day plan for me as a new machine learning engineer on the team described below. Keep it realistic for someone who has to learn the codebase, the data and the people before shipping anything. Days 1 to 30: understanding (which systems, which datasets, which owners to meet, which dashboards to read). Days 31 to 60: a first small contribution, for example a bug fix, an evaluation improvement or a monitoring gap closed, with how I would pick it. Days 61 to 90: a measurable project with a defined success metric and the risks. For each block give three to five outcomes, not activities, and one question I should ask my manager in the first week to check the plan. Mark any assumption about the team that I should verify. Keep it under 450 words.

Job description:
[paste job description]

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

Review my machine learning take-home submission as a senior engineer on the hiring panel would, before I send it. Be direct. Check for: data leakage between train and test, target leakage in features, a missing or weak baseline, evaluation metrics that do not match the business problem in the brief, unhandled class imbalance, randomness without fixed seeds, hard-coded paths, and claims in the README that the code does not support. Then check the README: can a reviewer run it in five minutes, and does it state the problem, the approach, the results and the limitations honestly? Output: a prioritized list of problems with the file and line or section for each, a suggested fix in one or two sentences, and a rewritten results and limitations section for the README that only claims what my code demonstrates.

The brief:
[paste the take-home instructions]

My code and README:
[paste or summarize]