Backend Engineer

Coris is building the AI-first trust and operations layer for global commerce. We partner with leading platforms, marketplaces, payment providers, and banks to transform how business onboarding, monitoring, and lifecycle decisions are made - using AI on the ground to drive faster, smarter actions with less friction.

One of our customers described us as Cursor + Lovable for risk teams: flagging bad actors, assisting in investigations, and autonomously acting to mitigate fraud losses in real time.

Backed by top-tier investors like Y Combinator, Lux Capital, Pathlight Ventures and founded by experts in the payments domain, Coris is reimagining how risk and ops gets done - not with legacy rule engines, but with domain-specific AI that thinks like your best risk analyst at scale. We help customers scale their expertise, move faster, and unlock growth without compromising safety.

We're growing quickly, with strong customer pull and adoption globally. If you're early in your career, allergic to busywork that isn't shipping, and want to learn at the frontier of AI and risk infrastructure faster than anywhere else - we'd love to talk.

Fraud detection and risk mitigation are fundamentally hard distributed systems problems:

• Adaptive adversaries. Fraudsters continuously change tactics, which means backend systems must support rapid iteration, safe rollouts, and real-time feedback loops  without breaking downstream consumers.
• Data sparsity and imbalance. Only a tiny fraction of events are fraudulent, but the systems handling them must be correct, auditable, and resilient across massive volumes of noisy, evolving data.
• Latency and scale constraints. Risk decisions must be made in tens of milliseconds across hundreds of millions of events per month, while keeping infrastructure costs predictable and failure modes well understood.

A lot of what makes this work is not glamorous. The signal lives behind poorly documented APIs, inconsistent data formats, and legacy systems that were never meant to talk to each other. This role is for an engineer who sees that schlep as the moat - who will happily dig into an undocumented payment processor integration and come out the other side having made the whole system smarter.

Backend + AI (~80%)

• Build and own Python/Django services that sit at the heart of Risk Decisioning and Execution.
• Model complex fraud/risk data in Postgres; write queries and aggregations that scale to billions of records.
• Build, operate, and enhance data ingestion pipelines from Stripe, Adyen, and other payment processors - as well as systems of record like Salesforce and Zendesk - handling near real-time volume.
• Roll up your sleeves on the non-sexy schlep work: integrating with poorly documented, inconsistent, and sometimes ancient APIs from legacy payment processors and platforms, and turning that mess into reliable signal.
• Build feature engineering pipelines that extract signals - including the non-obvious latent ones.

Frontend (~20%)

• Implement customer-facing features like AI chat interfaces and graph visualizations.
• Analyze, diagnose, and fix UI latency and performance bottlenecks.

• 1+ years building production systems in Python/Django with Postgres.
• Experience building frontend applications with React.js and Next.js.
• An AI-native way of working - you reach for LLMs and modern AI tooling by default to move faster, and you think about how AI reshapes the systems you build.
• A genuine willingness to do the unglamorous integration work that others avoid, and the grit to make undocumented, legacy systems behave.
• Very high energy and high agency - self-motivated, comfortable with long hours, and driven to go the extra mile to get things done.
• An experimental but practical mindset: ship fast, measure rigorously, iterate.
• A keen sense of information architecture and data presentation.

• Internship or early-career experience at a fast-scaling fintech or infra company (e.g., Stripe, Plaid, Brex, Adyen).
• Familiarity with payment infrastructure, merchant underwriting, or risk tooling.
• Hands-on experience fine-tuning or optimizing LLMs/SLMs, ideally in fraud, anomaly detection, or adversarial domains.
• Experience working closely with product or design in an early-stage team.

• Bias toward action, measurable impact, and staying ahead of adversaries.
• Everyone owns their code in prod - from training to inference to APIs.
• Fast iterations with real customer feedback; clear metrics drive decisions.
• In-person culture - 5 days a week in our Palo Alto office.
• Like any high-growth startup, we go well beyond the usual 40/50 hours per week. We need high-energy, high-agency people who go the extra mile to get things done.