AI Backend Engineer
Ketch
Software Engineering, Data Science
San Francisco, CA, USA
USD 120k-150k / year
Posted on Oct 22, 2025
About Ketch
We’re rebuilding the internet's data layer for the AI era. This starts with systems that analyze billions of events and make millions of decisions every day, enabling some of the largest brands in the world to leverage their data. Our platform dynamically engages users, orchestrates data directives across an entire ecosystem, and takes intelligent action on AI-driven insights. Protecting highly personal data across the data ecosystem requires infrastructure that can operate at the speed and complexity of modern, massively distributed systems. The result: real-time control and intelligence across billions of data interactions for companies, and direct control for you over how your personal data is collected and used.
Ketch is a well-funded Series B startup backed by top-tier investors and led by a leadership team with multiple exits. We’re passionate builders who work shoulder-to-shoulder with customers to understand their deepest data challenges and build elegant, scalable solutions.
Join us to build AI-driven distributed systems infrastructure that must never fail at massive scale, in the hardest runtime environment imaginable - agents that reason across hundreds of systems, pipelines that classify data flowing at enterprise velocity, and real-time intelligence layers that detect and act on risk as it happens.
Role Overview
As an AI Engineer at Ketch, you’ll build the intelligence layer that explains, governs, and secures how data moves across the modern enterprise. Ketch ingests terabytes of messy, high-stakes data from databases, pipelines, SaaS tools, websites, and mobile apps. Your job is to turn that chaos into clarity. You’ll design agents that reason across hundreds of systems, classify sensitive information, detect risks and data leaks in real time, and recommend actions that reshape how companies collect, store, and use data. These agents will make thousands of decisions per second across distributed environments where performance and trust are non-negotiable.
This is AI infrastructure at enterprise scale, blending backend engineering with applied AI to create fast, reliable services that deliver actionable intelligence. You’ll architect APIs and pipelines that transform raw data into structured insights, build feedback loops that get smarter with every interaction, and push the boundaries of what automated data governance can do.
We operate with deep personal ownership. You’ll ask sharp questions, work from first principles, and drive end-to-end solutions - from problem definition to architecture, modeling, deployment, and iteration. You’ll work shoulder-to-shoulder with product, design, and customer teams to make advanced AI capabilities feel simple, transparent, and trustworthy within the Ketch platform.
This is a hybrid position based in our San Francisco HQ 3 days a week
What You’ll Own
- Architect agentic, in-app intelligence that lets users interrogate, explore, and act on data classification insights - turning opaque enterprise data flows into real-time, explainable decisions.
- Build and scale classification pipelines that blend LLMs, embeddings, retrieval, and deterministic heuristics to classify documents, metadata, and records across dozens of systems and detect sensitive data and risk in real time.
- Build observability and feedback loops that monitor model behavior, track drift and quality, support human-in-the-loop validation, and continuously improve accuracy at scale.
- Develop APIs, microservices, and backend systems that power Ketch’s data privacy and permissioning platform, enabling companies to act on AI insights deterministically and in real time.
- Collaborate deeply with product teams and customers to translate ambiguous data-governance challenges into clear technical requirements and elegant solutions.
- Continuously evolve the intelligence layer behind Ketch, influencing architecture, modeling strategy, and the future of AI-driven data governance.
What We’re Looking For
- Strong backend engineering foundation in Python or Go - system design, API development, data pipelines, testing, CI/CD, and production cloud deployment.
- Hands-on experience building AI systems using LLMs, agentic frameworks, and RAG pipelines tailored for reasoning over large, messy enterprise datasets.
- Fluency in prompt engineering, fine-tuning, and evaluation techniques to push model accuracy and reliability in real-world deployments.
- Experience instrumenting observability (logging, metrics, model evaluations, drift detection) and designing feedback loops for human-in-the-loop workflows.
- Ability to partner with product, design, and frontend teams to transform complex AI capabilities into intuitive user experiences that feel simple and trustworthy.
- A proven learning mindset - comfortable picking up new tools, frameworks, and patterns and applying them to solve real customer problems.
- Degree in CS or equivalent experience, with a track record of building production systems that operate under real constraints.
120000 - 150000 USD a year
The estimated base salary range for this position is $120,000 to $150,000, which does not include the value of benefits or a potential equity grant. A wide range of factors are considered in making compensation decisions, including but not limited to skill sets, market conditions, experience and training, licensure and certifications, and business and organizational needs
We do not accept resumes from headhunters, placement agencies, or any 3rd parties. All submissions will be considered a gift and no fee will be due.