SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Jeeves is a stablecoin-native banking platform serving global enterprises with corporate cards, payments, treasury, and spend management. The company processes over $5B in annualized volume, supports payouts to 190 countries, and operates one of the fastest-growing stablecoin payment networks. Customers include BMW, H&M, Lululemon, Burger King, Kavak, and XP, with over 80% using multiple Jeeves products. The company has raised $400M+ from top-tier investors including Andreessen Horowitz, Y Combinator, Coinbase Ventures, and others.
As a Senior AI Engineer, you will own complete AI workflows end to end—from design through launch and ongoing iteration. This is a hands-on role for AI-native engineers who use coding agents and LLM tools daily and understand their limitations.
Key responsibilities:
**Own AI Workflows End to End:** Design agentic and LLM-based systems combining extraction, retrieval, reasoning, and tool use for multi-step work with clear human-in-the-loop points. Write design docs, make build-vs-buy and model choices, and set success metrics for each workflow.
**Build Reliable AI in Production:** Develop production-grade LLM pipelines with prompt and context design, structured outputs, validation, fallbacks, and confidence scoring. Integrate AI services cleanly with Jeeves's backend via clear API contracts, retries, graceful degradation, and per-customer data isolation. Manage cost and latency across models.
**Measure, Monitor, and Improve:** Build evaluation sets and automated evals for every workflow. Instrument AI components with logging, tracing, dashboards, and alerts. Maintain audit trails meeting regulated financial product standards.
**Raise the Bar for AI Engineering:** Set patterns, shared tooling, and practices for other engineers. Demonstrate effective use of coding agents and AI tools in day-to-day engineering. Review peers' AI system designs and share learnings.
You will work closely with Product, Backend Engineering, and customers, but won't wait for someone to hand you a spec. This is not a research role and not for someone wanting a narrow, well-defined ticket queue.
**Requirements:**
- 7+ years of professional software engineering experience, including at least 2 years building and operating LLM or AI-powered systems in production
- Track record of owning a large system or workflow end to end, from scoping and design through launch and iteration, with limited direction
- Hands-on experience shipping LLM-powered applications with APIs such as Anthropic, OpenAI, or similar, including structured outputs, error handling, and evaluation
- Experience designing agentic or multi-step AI workflows (tool use, orchestration, human review steps)
- Strong proficiency in Python, plus solid backend fundamentals: REST APIs, PostgreSQL or similar relational databases, async patterns, and a major cloud provider (AWS, GCP, or Azure)
- Experience with observability for AI systems: logging, tracing, dashboards, and quality monitoring
- Professional fluency in English, written and spoken
