About the company
Our client is a fast-growing software company.
The role
Raydar is recruiting for this role on behalf of our client. Own the applied AI layer of a software platform, covering data retrieval, structured extraction, quality measurement and production monitoring. You will build dependable AI services on top of hosted language models and help set the standards for testing them and keeping them safe in live use.
What you'll do
- Build and run production AI services and pipelines that convert unstructured inputs into structured results.
- Design retrieval and context-assembly approaches for language model features.
- Select among model providers and manage latency, cost, retries and failure handling.
- Create evaluation datasets, regression tests, launch gates and fallback paths to keep output quality high.
- Investigate problems stemming from inputs or model behavior, and add guardrails that reduce errors and enforce constraints.
- Develop multi-step, tool-using workflows and monitor them in production.
- Turn loosely defined product goals into experiments, measurable results and shipped improvements.
- Talk with users directly, collect their feedback and refine features accordingly.
Requirements
What we're looking for
- 4 to 6+ years building production software, machine learning systems or applied AI systems.
- Strong Python skills, including building and maintaining services and using async patterns.
- A track record of shipping AI/ML systems to production with sustained ownership, beyond internal tooling.
- Hands-on experience creating evaluation suites, benchmarks or automated testing and delivery workflows for machine learning products.
- Proven experience with retrieval-augmented generation, retrieval or agent orchestration.
- Experience turning hosted language model APIs into product behavior through structured outputs, tool use or multi-step workflows.
- Ability to think about a whole system from incoming data through to what the user sees.
- Experience iterating on features from direct user feedback, with clear written and verbal communication.
- Experience leading larger projects, judged by scope, complexity and business importance.
- A pragmatic approach to refactoring versus shipping, build versus buy, and managing technical debt.
- A Bachelor's degree or higher in a technical discipline such as computer science or engineering.
- An understanding of what being a founding engineer involves.
- Ability to work on-site five days a week.
Bonus points
- Experience with embeddings, hybrid search, chunking and reranking.
- Experience making agentic workflows dependable when steps or tools fail.
- Experience pulling trustworthy structured information out of long or messy documents.
- Experience working with varied input formats, such as images, audio or video content.
- Familiarity with a typed language such as Go, C++, Java, Scala or C.
- Exposure to business process analysis or workflow software.
- Regular use of AI-assisted coding tools.
Benefits
Compensation and benefits
- Base salary: USD 180,000 to 275,000 per year
- Equity
- Benefits package
Location and work model
- San Francisco, CA, United States
- On-site, 5 days per week in office
- Full-time
Similar Jobs
What you need to know about the San Francisco Tech Scene
Key Facts About San Francisco Tech
- Number of Tech Workers: 365,500; 13.9% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: Google, Apple, Salesforce, Meta
- Key Industries: Artificial intelligence, cloud computing, fintech, consumer technology, software
- Funding Landscape: $50.5 billion in venture capital funding in 2024 (Pitchbook)
- Notable Investors: Sequoia Capital, Andreessen Horowitz, Bessemer Venture Partners, Greylock Partners, Khosla Ventures, Kleiner Perkins
- Research Centers and Universities: Stanford University; University of California, Berkeley; University of San Francisco; Santa Clara University; Ames Research Center; Center for AI Safety; California Institute for Regenerative Medicine
