Claude prompts for computer vision engineer job searches

I am applying for the computer vision engineer role below. Rewrite my resume to match it using only experience that is already on my resume. Do not invent models, datasets, hardware, frameworks or accuracy numbers. The posting may ask for detection, segmentation, tracking, 3D reconstruction, edge deployment or specific frameworks; 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 task, the approach and the measured result; and the Gaps list with one honest sentence per gap about adjacent work I have done. Keep every job, title and date as it is.

Job description:
[paste job description]

My resume:
[paste your resume]

Write a cover note of at most 120 words for the computer vision engineer role below. Use only facts from my resume and my notes. No invented results, no "passionate", no "state of the art". Structure: one sentence that shows I understand the visual problem this team solves and its constraints (camera, latency, hardware; take it from the job description), two sentences on the most relevant vision system I have built and what it did, 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 computer vision 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 C++ on image manipulation (for example computing IoU, non-maximum suppression, or a convolution by hand), two fundamentals questions drawn from the job description (for example why batch normalization helps, how anchor-based and anchor-free detection differ, what mAP measures and hides, how to handle class imbalance in segmentation, or camera intrinsics and extrinsics), one question about a project on my resume, and one question on running a model on constrained hardware. 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 a computer vision system design interview with me for the role below. Pick a problem that fits the company (for example defect detection on a production line, person tracking across cameras, document layout understanding, or perception for a vehicle) and describe it in two sentences. Guide me one stage at a time, waiting for my answer: requirements and the cost of each kind of error, cameras and capture conditions, the data collection and labeling plan, model choice and why, augmentation and handling domain shift, offline metrics and a validation set that reflects deployment, latency and hardware budget, deployment and versioning, monitoring for drift, and the feedback loop for new failure cases. After each stage, point out what an experienced engineer would have raised that I missed. Finish with a one-page summary of the design 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 a computer vision 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 (a model that worked offline and failed in the field, a labeling or data quality problem, a hardware or latency constraint that forced a trade-off, disagreeing with a teammate about approach, a deadline, a mistake you owned, learning a new domain quickly, and working with hardware or field teams). 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 computer vision project, first person, plain language, aimed at a hiring manager. Use only what is in my notes. Where something important is missing (the task, dataset size and how it was collected and labeled, the baseline, the metric and its numbers, inference time and hardware, failure cases), insert a placeholder in square brackets and list the placeholders at the end. Structure: the problem and its constraints, the data and what was hard about it, the approach and what I tried first, the results against the baseline with the metric named, example failures and what they taught me, and what I would do next. Suggest a title, a two-sentence README summary, three honest resume bullets, and which two images or figures would make the write-up clearer.

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

I have an offer for a computer vision 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 (hardware startup, large tech, automotive, or medical) 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, compute and data access, whether the role involves field work or travel, 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 computer vision engineer on the team below. Keep it realistic: I have to learn the data pipeline, the labeling process, the deployed models and the hardware before shipping. Days 1 to 30: which models are in production and how they are measured, where the data comes from, how labels are made and checked, and what the top failure cases are. Days 31 to 60: a first contribution, for example a validation set that better reflects deployment, a labeling guideline fix, or a measured accuracy or latency improvement. 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]

Help me plan the data side of the computer vision task below, the way I would present it in a take-home or a design round. Ask me first for anything you need: the task, the capture setup, the cost of each kind of error, and what data already exists. Then produce: (1) a collection plan that covers the conditions the model will see in deployment (lighting, angles, occlusion, devices, seasons, rare classes) with rough proportions; (2) a labeling guideline of ten or fewer rules, with the ambiguous cases spelled out; (3) how I would measure label quality and inter-annotator agreement; (4) a split strategy that avoids leakage (by scene, device, time or subject, whichever applies) and why; (5) which augmentations are safe for this task and which would change the label; (6) what I would monitor after deployment to find new failure cases. Under 600 words, and say what I could not conclude from a dataset of the size I have.

The task:
[describe the feature or take-home]