Research Scientist II

Remote from: USA
Salary, yearly, USD: 160,000 - 185,000
Department: Data Science & Analytics
Employment type: Full Time,
Job posted: 28 Jun 2026
Apply before: 28 Jul 2026
Experience level: Midweight
Views / Applies: 11 / 2

Leading the way to the future of voice by establishing the standard for security, identity, and trust for every voice interaction.

Computer & Network Security
2011

AI Summary

Pindrop is seeking a Research Scientist II to join its Fraud Research team, focusing on improving fraud detection and scam prevention across voice and IVR interactions. The role involves building fraud risk models using audio, behavioral, and metadata signals, analyzing fraud patterns, and developing a scam detection stack. The ideal candidate has an advanced degree in a quantitative field and 3+ years of experience in machine learning, fraud detection, or related domains. They will collaborate with cross-functional teams, support high-priority fraud investigations, and contribute to reproducible research workflows. This position offers a chance to work on high-impact security problems for major enterprise customers.

Role DNA

Job Complexity

Easy Hard

Pace & Pressure

Relaxed Fast-paced

Autonomy Level

Guided Full Ownership

Communication Load

Independent Highly Collaborative

AI Insight The role demands an advanced degree (Master's or PhD), 3+ years of professional experience in machine learning or fraud detection, and the ability to handle ambiguous, fast-evolving fraud behavior, making it highly challenging.

Salary Analysis

AI Insight The offered salary range of $160,000 to $185,000 is competitive for a Research Scientist II role in the US market, aligning well with the median of $172,500 and reflecting the specialized fraud detection domain.

Key Skills

Machine Learning Fraud Detection Deep Learning Python PyTorch Signal Processing Anomaly Detection NLP Research Production ML

Cover Letter Sample

Dear Hiring Manager,

I am excited to apply for the Research Scientist II position at Pindrop. With a PhD in Computer Science and over 4 years of experience in fraud detection and machine learning, I have developed robust models to combat financial fraud using voice and behavioral signals. My work at [Previous Company] involved designing anomaly detection systems that reduced fraud by 30% and improved customer trust.

I am particularly drawn to Pindrop's mission to restore trust in the AI era, and I believe my background in building scalable ML pipelines and analyzing fraud patterns aligns well with the needs of your Fraud Research team. I have extensive experience with PyTorch and Python, and I am skilled in translating research findings into production-ready solutions.

I look forward to the opportunity to contribute to Pindrop's innovative identity trust platform and drive measurable impacts on fraud prevention for leading enterprises.

Sincerely,
[Your Name]

Possible Interview Questions

Describe a time when you had to research and develop a fraud detection model from scratch. What was your approach, and how did you measure its success?

At my previous company, I was tasked with detecting synthetic voice fraud. I started by analyzing existing call data to identify patterns, then explored features like spectral and prosodic cues. I built a hybrid model using an autoencoder for anomaly detection and a classifier for known fraud. Success was measured by precision-recall curves and a 20% reduction in false positives, which saved the company $500k annually.

How do you handle ambiguous or noisy data when building a research prototype? Can you give an example?

In fraud detection, data is often noisy with missing labels. For a project on scam detection, I used semi-supervised learning with a consistency regularization loss. I also implemented rigorous data cleaning and augmentation. This approach improved model robustness and we achieved a 15% boost in recall on noisy test sets.

Explain a complex machine learning concept to a non-technical stakeholder. How do you ensure they understand the implications?

I once explained a deep learning model for voice liveness detection to a product manager. I used an analogy of a voiceprint vs. a password, and how the model distinguishes real vs. recorded voices by analyzing subtle artifacts. I focused on impact: reduced fraud rates without adding friction. I also created visualizations showing decision boundaries. The key is to connect technical details to business outcomes.

Describe your experience with reproducible research. What tools or practices do you use?

I believe in version control for both code and data, using Git LFS for datasets. I use Docker for environment reproducibility and Jupyter notebooks with clear documentation. For experiments, I track parameters and results with MLflow. This ensures that any team member can replicate my experiments and build upon them.

How would you approach building a scam detection system that needs to adapt to evolving fraudster tactics?

A robust system requires continuous retraining and feedback loops. I would design a pipeline with automatic feature extraction and online learning components. Additionally, implementing active learning to label suspicious calls quickly. I would also monitor drift in model performance and set up triggering mechanisms for retraining. Collaboration with investigation teams is crucial to stay ahead of new tactics.

Who We Are

Pindrop is the Real Human + Right Human® Identity Trust Platform for the AI era. As AI-driven fraud and deepfakes erode trust in digital communication, Pindrop delivers continuous identity verification and deepfake detection across voice, video, and digital interactions in real time.

Enterprises rely on Pindrop to secure billions of high-risk customer interactions each year, including top U.S. banks, as well as leading insurers and healthcare providers. Powered by models trained on more than 1.5 billion real-world interactions annually and protected by 300+ patents, Pindrop restores trust while reducing fraud, lowering operational costs, and improving customer experience.

Recognized by TIME as one of the Top 10 Most Influential Software Companies of 2026 and by Inc. for Best in Business for Innovation, Pindrop is backed by leading investors including Andreessen Horowitz, IVP, and CapitalG.

What you’ll do

As a Research Scientist II on the Fraud Research team, you will help improve how Pindrop detects, scores, and investigates fraud and scams across voice and IVR interactions. You will work on applied machine learning problems that directly impact fraud and scam prevention for major enterprise customers, balancing core model development with real-world investigation and analysis. In this role, you will:

Build and improve fraud risk models and scoring systems using a combination of audio, behavioral, and metadata-based signals.
Analyze fraud patterns across customer environments and translate findings into measurable improvements in model performance, investigation workflows, or mitigation strategies.
Research and build a scam detection stack, from conception to realization.
Partner with engineering and cross-functional teams to move successful research into production and improve fraud outcomes in live environments.
Support high-priority fraud investigations by analyzing system behavior, fraudster attack patterns, and detection gaps, then recommending practical next steps for our customers.
Improve the quality and precision of fraud-related identity signals, including voice-based indicators and repeat-offender detection.
Design and maintain reproducible research workflows, internal tools, and evaluation pipelines that help the team experiment efficiently and measure impact clearly.
Contribute to technical reviews, knowledge sharing, and research documentation that helps the broader organization understand and apply your work.
Contribute to adjacent innovation areas, including emerging AI-assisted fraud-analysis workflows, when relevant to team priorities.

Who you are

You are persistent, curious, and scientifically rigorous, especially when working through ambiguous data, noisy signals, or fast-evolving fraud behavior.
You are comfortable owning research workstreams from problem definition through experimentation, analysis, and recommendation.
You communicate clearly with both technical and non-technical partners, and you can explain tradeoffs, assumptions, and results in a practical way.
You care deeply about reproducibility, documentation, and building research that can stand up in real production settings.
You are motivated by high-impact security and fraud problems and want your work to influence real customer outcomes.

Your skill-set

Must-Haves:

Advanced Degree (Master’s or PhD) in Computer Science, Mathematics, Statistics, Engineering, Artificial Intelligence, or a related quantitative field, or equivalent applied research experience.
3+ years of professional experience in machine learning, large-language models, fraud detection, natural language processing, risk modeling, speech or signal processing, anomaly detection, or a closely related domain.
Strong Python skills and experience building research tooling, experimentation frameworks, or model evaluation workflows.
Hands-on experience with modern machine learning frameworks such as PyTorch, TensorFlow, or Keras.
A track record of translating research findings into practical improvements, whether in models, decision systems, or production-facing recommendations.
Foundational knowledge of fraud, identity, consumer scams, authentication, risk scoring, or customer security concepts.

Nice-to-Haves:

Experience working on fraud or scam detection in voice, IVR, contact center, authentication, or adjacent trust and safety environments.
Experience working on building and/or fine-tuning multi-modal foundation models.
Experience improving precision and recall in real-world detection systems, including thresholding, scoring, watchlists, or entity-resolution style signals.
Familiarity with metadata-driven risk signals such as telephony, carrier, device, account, or behavioral indicators.
Experience with sequence modeling, event-based risk modeling, or other approaches used to detect evolving attack behavior.
Familiarity with LLM-enabled research workflows, retrieval systems, or observability tools used to support analyst or fraud-investigation productivity.
Working knowledge of C/C++, Go, or other production-oriented languages.

What’s in it for you

This is a high-impact opportunity to join Pindrop’s Research organization and work on fraud problems that matter in the real world. Your work will directly influence how we detect fraud, investigate suspicious behavior, and improve protection for major financial institutions and other enterprise customers.

You’ll collaborate closely with strong technical peers across research and engineering, work on meaningful applied machine learning challenges, and help shape the next generation of fraud detection capabilities at Pindrop.

What we offer

As a part of Pindrop, you’ll have a direct impact on our growing list of products and the future of security in the voice-driven economy. We hire great people and take care of them. Here’s a snapshot of the benefits we offer:

Competitive compensation package, including RSUs (Restricted Stock Units) for all employees, so everyone shares in our long-term success.
Remote-first environment – giving you flexibility and autonomy in how you structure your day.
While we work flexibly, we prioritize meaningful in-person moments through regular team on-sites, company-wide events, and intentional gatherings that foster connection, collaboration, and shared success.
Unlimited Paid Time Off (PTO)
Generous health and welfare plans to choose from – including one employer-paid “employee-only” plan!
Best-in-class Health Savings Account (HSA) employer contribution
Low-cost vision and dental plans for you and your family, providing comprehensive coverage and peace of mind.
Paid Parental Leave – Including birth, adoptive & foster parents
One year of diaper delivery for your newest addition to the family! It’s our way of welcoming new Pindroplets to the family!
Recurring monthly phone and internet allowance to help cover essential connectivity costs and support flexible work.
Enhanced fertility and GLP-1 benefits to support family-building journeys and personalized health needs.
Annual Learning & Development stipend to support your professional growth, skill-building, certifications, and continued education.

This position will be posted for 60 days after 6/26/26.
#LI-Remote

Please note that the base pay range is a general guideline only. Pindrop considers factors such as (but not limited to) scope and responsibilities of the position, a candidate’s work experience, education/training, and key skills, as well as market and business considerations, when extending an offer.

US Base Pay Range

$160,000—$185,000 USD

Not sure if this is you?

We want a diverse, global team, with a broad range of experience and perspectives. If this job sounds great, but you’re not sure if you qualify, apply anyway! We carefully consider every application and will either move forward with you, find another team that might be a better fit, keep in touch for future opportunities, or thank you for your time.

AI – A Transformative Force

At Pindrop, we view artificial intelligence as a transformative force that, when harnessed responsibly, can unlock unprecedented value for our customers, partners and society and enable and empower us to continue to deliver cutting-edge technology to combat fraud and unblur the lines between what it means to be human versus machine.

Pindrop may use AI tools to help prioritize job applications for human review. The AI tool may analyze your work experience and skills to assess fit for the role, but does not consider your name or contact details. Applications with the strongest match to job requirements are prioritized for human review; not all applications may be individually reviewed.

Pindrop is an Equal Opportunity Employer

Here at Pindrop, it is our mission to create and maintain a diverse and inclusive work environment. As an equal opportunity employer, all qualified applicants receive consideration for employment without regard to race, color, age, religion, sex, gender, gender identity or expression, sexual orientation, national origin, genetic information, disability, marital and/or veteran status.

Apply now >