Coris is building foundational AI infrastructure for merchant risk and operations.
We help software platforms, fintechs, and payment providers onboard and monitor merchants more efficiently — turning what used to take days into workflows that run in seconds. Our unified platform combines rich data and AI agents to automate risk decisions at scale.
We’re growing quickly, with strong customer pull and adoption globally. The category is being defined in real time, and the opportunity in front of us is massive. If you're excited by speed, ownership, and building at the frontier of AI and risk infrastructure, we'd love to talk.
We’re backed by Y Combinator, Lux Capital, Pathlight Ventures, and other top investors.
About the RoleFraud detection and risk mitigation is a uniquely hard ML problem:
Adaptive adversaries - fraudsters continuously evolve tactics, so models must adapt faster than static rules.
Data sparsity and imbalance - only a tiny fraction of transactions are fraudulent, but they cost millions.
Latency and scale - decisions need to happen in tens of milliseconds at hundreds of millions of events per month, without ballooning infra costs.
This role is for someone who wants to optimize language models for fraud/risk contexts and build the backend infra that productionizes them at scale.
This role is based in Palo Alto, CA. We work in a hybrid model (3 days/week in the office).
What You’ll doAI/ML (~50%)Fine-tune, distill, and quantize LLMs and small language models (SLMs) for fraud detection tasks: entity resolution, anomaly detection, customer communication classification, synthetic data generation.
Optimize inference so our models run fast and cost-efficiently in production - using techniques like lightweight fine-tuning (LoRA/PEFT), quantization to smaller precisions, and modern serving frameworks (e.g. vLLM, TensorRT)
Build training/eval pipelines for fraud models that balance recall (catch fraud) with precision (minimize false positives).
Create golden datasets, adversarial test sets, and online/offline evaluation harnesses that mirror real-world fraud evolution.
Build feature engineering pipelines extracting various signals including the non-obvious latent ones.
Architect and own Python/Django services that integrate model predictions directly into customer-facing APIs.
Model complex fraud/risk data in Postgres; ensure queries and aggregations scale to billions of records.
Build/Operate/Enhance data ingestion pipelines from Stripe, Adyen, and other payment processors, handling near real-time volume.
Ensure observability with logs, metrics, and drift detection to catch when fraud tactics change.
3+ years building production systems in Python/Django with Postgres.
Hands-on experience fine-tuning and optimizing LLMs/SLMs, ideally in fraud, anomaly detection, or adversarial domains.
A track record of reducing latency/cost in ML inference without compromising accuracy.
Comfort working across the stack - from PyTorch profiling to Django APIs.
An experimental but practical mindset: ship fast, measure rigorously, iterate.
Prior work with imbalanced datasets (e.g., 1 in 10,000 fraud cases).
Knowledge of feature stores, online learning, and temporal aggregation for fraud models.
Familiarity with regulatory requirements around PII, KYC/AML, and compliance in financial data.
