Time since we first saw it
Day 4
Early. Similar jobs usually come down between day 7 and day 60.
From 12,342 similar postings that came down. Coming down is not always a hire.
Dublin, Ireland
Actively hiring, first seen by us 4 days agoWork setup in the employer’s posting: HybridFrom the employer’s posting
Employment type in the employer’s posting: FullTimeFrom the employer’s posting
Own document fraud research problems from start to finish
Build detectors for edited, tampered and AI-generated images and documents
Design rigorous evaluations, labelling and backtesting on production traffic
Reduce false positives by tuning thresholds and detector combinations
Work on LLM-based fraud detection, including model and tool evaluations
Own research problems in document fraud detection from start to finish
Help build detectors for fraud detection algorithms, with a special focus on image file types, such as edited or tampered images, JPEG manipulation and AI-generated documents
Design rigorous evaluation: sampling strategies to estimate recall on unlabelled production traffic, ground-truth labelling, precision/recall trade-offs at low fraud rates, backtesting and shadow experiments
Reduce false positives by understanding what drives them, then tuning thresholds, detector combinations and per-customer configurations
Work on LLM-based fraud detection: model and tool evaluations, agent and prompt experiments, customer-level analysis and reactive fixes
3+ years applied research, ML or data science in industry, with models you built running in production.
Experience in fraud, risk, anomaly detection or other adversarial domains.
Strong statistics and experimental design: working with data from real scenarios, with missing labels, errors and biases. Ability to run experiments and evaluate results, to know what numbers matter and how to communicate them.
Experience with document data parsing: OCR, layout models, object detection, bonus if applied to financial/identity documents
Hands-on experience with computer vision and image analysis.
Experience building data-labelling pipelines.
- 3+ years applied research, ML or data science in industry, with models you built running in production. - An MSc or PhD in a quantitative field (CS, statistics, physics, maths or similar), or equivalent experience. - Strong statistics and experimental design: working with data from real scenarios, with missing labels, errors and biases. Ability to run experiments and evaluate results, to know what numbers matter and how to communicate them.
From the employer’s posting.
At Inscribe, we're on a mission to catch fraud with confidence.
In the employer’s words · Read in context
Actively hiringFirst seen by us 4 days ago, still listed, and not a repost of an earlier posting.
These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.
Day 4
Early. Similar jobs usually come down between day 7 and day 60.
From 12,342 similar postings that came down. Coming down is not always a hire.
2 open jobs
Open jobs by the week we first saw them, last 12 weeks.
Hiring recordAdd your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.
Tech Stack These are the main technologies we work with. We are not looking for someone with experience in all these as we believe in learning on the go, we require however candidates to have production experience with Python, SQL and AWS. - Languages: Python (Django), SQL
These are the main technologies we work with. We are not looking for someone with experience in all these as we believe in learning on the go, we require however candidates to have production experience with Python, SQL and AWS. - Languages: Python (Django), SQL - Cloud: AWS (RDS/Aurora, ECS, S3, Bedrock, etc.)
- Practical experience with LLMs and VLMs: evaluating and comparing models, building pipelines around them, and being able to tell when they are not the best choice. - Good Python (PyTorch, NumPy, pandas) and SQL. You’re comfortable working in a production codebase and shipping with engineers, not handing off notebooks. - Strong data intuition: you look at raw examples, find patterns and failure modes, and don’t trust a metric you haven’t checked against real data.
- Languages: Python (Django), SQL - Cloud: AWS (RDS/Aurora, ECS, S3, Bedrock, etc.) - Observability: Datadog, Grafana
- Observability: Datadog, Grafana - AI Platforms: Anthropic, AWS Bedrock About You
- Cloud: AWS (RDS/Aurora, ECS, S3, Bedrock, etc.) - Observability: Datadog, Grafana - AI Platforms: Anthropic, AWS Bedrock
Complete your application on jobs.ashbyhq.com. The employer’s form will show what is required.
Already applied? Track this application
At Inscribe, we're on a mission to catch fraud with confidence. In 2017, we set out to build the first document fraud detection product. Today, we process millions of applications each year and work with many of the leading fintechs and banks across the U.S. We believe the game of cat-and-mouse in fraud requires a fundamentally new approach. With care for our customers, attention to detail, and grounded execution, we’re reimagining how fraud is detected and prevented.
Inscribe is trusted by leading banks and fintechs, including Coinbase, Plaid, Bluevine, and Ramp. Inscribe is backed by Threshold Ventures, Uncork Capital, Y Combinator, Crosslink Capital, and Foundry, and is headquartered in San Francisco, CA.
Fighting fraud is a continuous battle. We’re hiring a Research Scientist to develop our fraud detection capabilities by investigating new methods, improving the ones we have and, most importantly, turning research ideas into production algorithms.
The documents that pass through Inscribe are many and varied in content and format. Images are a particularly tricky file type and we are always looking for ways to extend our catch rate on them. We look for someone eager to quickly test prototypes, solve issues as they come, learn on the go.
Research at Inscribe is not a siloed function but it sits at the heart of our tech team and collaborates very strictly with engineering: anyone is empowered to come up with ideas and try them, fraud fighting is a shared goal. Research informs what we do, rigorously tests ideas, quickly discards those that don’t work and communicates findings in an approachable way.
Own research problems in document fraud detection from start to finish
Help build detectors for fraud detection algorithms, with a special focus on image file types, such as edited or tampered images, JPEG manipulation and AI-generated documents. Combine classical forensics, deep learning and VLMs.
Design rigorous evaluation: sampling strategies to estimate recall on unlabelled production traffic, ground-truth labelling, precision/recall trade-offs at low fraud rates, backtesting and shadow experiments.
Find and sort failure modes by digging into real customer documents, and turn them into labelled datasets and new detection work.
Work on LLM-based fraud detection: model and tool evaluations, agent and prompt experiments, customer-level analysis and reactive fixes.
Reduce false positives by understanding what drives them, then tuning thresholds, detector combinations and per-customer configurations.
Analyse our production data to detect anomalies and emerging trends in how fraud techniques change across customers and markets, and turn those insights into new detection work and product features.
Shape the research roadmap: follow the literature, propose new detection bets, and decide what to stop as well as what to start.
Partner with fraud analysts, product and engineering so research gets to production and changes customer outcomes.
Write clear research docs and share findings in the research syncs.
These are the main technologies we work with. We are not looking for someone with experience in all these as we believe in learning on the go, we require however candidates to have production experience with Python, SQL and AWS.
Languages: Python (Django), SQL
Cloud: AWS (RDS/Aurora, ECS, S3, Bedrock, etc.)
Observability: Datadog, Grafana
AI Platforms: Anthropic, AWS Bedrock
Essential
3+ years applied research, ML or data science in industry, with models you built running in production.
An MSc or PhD in a quantitative field (CS, statistics, physics, maths or similar), or equivalent experience.
Strong statistics and experimental design: working with data from real scenarios, with missing labels, errors and biases. Ability to run experiments and evaluate results, to know what numbers matter and how to communicate them.
Hands-on experience with computer vision and image analysis.
Practical experience with LLMs and VLMs: evaluating and comparing models, building pipelines around them, and being able to tell when they are not the best choice.
Good Python (PyTorch, NumPy, pandas) and SQL. You’re comfortable working in a production codebase and shipping with engineers, not handing off notebooks.
Strong data intuition: you look at raw examples, find patterns and failure modes, and don’t trust a metric you haven’t checked against real data.
A pragmatic, business-aware approach: you ship small improvements often, connect research to customer impact, and explain results clearly to non-technical people.
Highly sought
Experience in fraud, risk, anomaly detection or other adversarial domains.
Image forensics: tamper detection, compression artefacts, or detecting AI Generated images.
Experience with document data parsing: OCR, layout models, object detection, bonus if applied to financial/identity documents
Experience building data-labelling pipelines.
Evaluating agentic or LLM-reasoning systems.
Time series analysis (anomaly and trend detection) and unsupervised or self-supervised representation learning, given how much of our data is unlabelled.
At Inscribe, we are building a company and culture where everyone can produce their best work. Here are a few of our benefits and perks:
Competitive salary and meaningful equity
Comprehensive healthcare
Unlimited vacation policy
Paid parental leave
401(k) and pension plans
Monthly wellness stipend
Inscribe provides equity employment opportunities to all employees and applicants and prohibits discrimination and harassment of any type with regards to race, color, religion or religious belief, ethnic or national origin, nationality, sex, genetics, gender, gender identity, sexual orientation, disability, age, military or veteran status, disability status, or any other basis protected by applicable local, state, or federal laws or prohibited by company policy.
New Data Scientist postings at the employers we follow are up 3% over the last 6 weeks compared with the 6 before.
Each bar is one week of new postings. The darkest bars are the last 6 weeks.
Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.
We file this job under Data Scientist, by the work the posting describes.
Data scientists use statistics and models to answer harder questions, such as whether a change worked, what demand will look like next quarter, or which customers are likely to leave.
Postings usually ask for Python or R, SQL, statistics, experiment design and common machine learning methods.
Unlike an ML engineer, a data scientist's main output is often an analysis or a first model, not software running inside a product.
Source: US Bureau of Labor Statistics, Occupational Employment and Wage Statistics (May 2025) and Employment Projections (2025 to 2035). Occupation code 15-2051.
Selected passages from the saved posting. Check the full description for conditions and exceptions.
No pay amount identified in the saved description.
Dublin, Ireland
Working pattern and location restrictions need checking in the full posting.
No clear work-authorization passage found. Eligibility is unconfirmed.