Job alert: Y Combinator-backed Coris hiring AI engineer for $125K-$160K fraud detection role

Coris, a Y Combinator-backed fintech startup, is hiring an AI Engineer to build machine learning systems for fraud detection and risk management in global commerce. The role combines advanced AI model optimization with backend infrastructure development, targeting candidates with 3+ years of experience in Python, PyTorch, and production ML systems for a salary range of $125K-$160K plus equity.

What you should know: The position focuses on solving complex fraud detection challenges using AI-first approaches rather than traditional rule-based systems.

• Coris partners with major platforms like GoFundMe, Kajabi, and Clio to automate merchant onboarding and risk decisions.
• The company describes itself as “Cursor + Lovable for risk teams,” helping detect fraud and assist investigations in real-time.
• Founded in 2022, the 9-person team is backed by Y Combinator, Lux Capital, and Pathlight Ventures.

The technical challenge: Fraud detection presents uniquely difficult machine learning problems that require specialized solutions.

• Adaptive adversaries: Fraudsters continuously evolve tactics, requiring models that adapt faster than static rules.
• Data sparsity: Only a tiny fraction of transactions are fraudulent, but they cost millions in losses.
• Latency requirements: Decisions must happen in tens of milliseconds while processing hundreds of millions of events monthly.

In plain English: Think of fraud detection like playing chess against opponents who constantly change the rules mid-game. Traditional systems use fixed playbooks (rule-based approaches), but AI models can adapt and learn new patterns as fraudsters develop new tricks. However, finding fraud is like searching for a few needles in massive haystacks—and you need to do it lightning-fast without mistakenly flagging legitimate customers.

Key responsibilities: The role splits evenly between AI/ML development and backend infrastructure work.

• Fine-tune and optimize large language models (LLMs) and small language models for fraud detection tasks including entity resolution, anomaly detection, and synthetic data generation.
• Build Python/Django services integrating model predictions into customer-facing APIs.
• Create training pipelines that balance recall (catching fraud) with precision (minimizing false positives).
• Architect data ingestion systems handling real-time volume from payment processors like Stripe and Adyen.

What they’re looking for: Candidates need hands-on experience with production ML systems and full-stack development.

• 3+ years building production systems in Python/Django with Postgres database management.
• Experience fine-tuning and optimizing LLMs and small language models, ideally in fraud or adversarial domains.
• Track record of reducing ML inference latency and costs without compromising accuracy.
• Comfort working across the full stack from PyTorch profiling to Django APIs.

Success metrics: The company expects measurable impact within 3-6 months of hiring.

• Deploy a distilled/quantized fraud model with 2-3x lower latency and cost than baseline.
• Build robust pipelines for fine-tuning and evaluating fraud models.
• Launch Django services powering real-time fraud scoring APIs integrated with payment data flows.

Work culture: The startup emphasizes high-energy, high-agency individuals willing to exceed typical work hours.

• In-person culture requiring at least 4 days per week in their Palo Alto office.
• Bias toward action with fast iterations based on customer feedback.
• Full ownership model where engineers maintain their code from training to production.