AI Product Engineer

Anara Labs, Inc; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

A leading tech company in San Francisco is seeking a full-stack engineer to drive AI agent workflows. This role involves working with modern tech stacks like Next.js and AWS, optimizing system performance and collaborating with a dynamic team. If you are a hands-on builder comfortable in a startup environment, we want to hear from you. We're also open to sponsoring visas for candidates interested in relocating.

Benefits

Premium healthcare (medical, dental, etc.)

Flexible working hours

Office space with a view

Qualifications

• Experience shipping complex backend and AI/ML features.
• Worked in a high-growth, fast-paced environment ideally at a startup.
• Hands-on experience with LLMs, RAG, and agent architectures.

Responsibilities

• Own the design and optimization of AI agent workflows.
• Collaborate on improving response quality and system performance.
• Establish best practices for prompt engineering and model deployment.

Skills

AI/ML features

Full stack development

Prompt engineering

System performance optimization

Tools

Next.js

AWS

Python

Tailwind CSS

Prisma

Job description

We’re looking for a full-stack engineer to own and drive AI agent workflows at Anara (formerly Unriddle). This is an opportunity to reinvent how scientists discover information and collaborate. You'll build the technical foundation for features that will transform scientific research for decades to come.

Our tech stack consists of Next.js, TRPC, Tailwind CSS, Drizzle and Prisma for databases, AWS (SST/EC2), NextAuth, Turborepo and Python.

We value hands-on experience over fancy credentials. We’re most interested in engineers who have built interesting side projects or contributed to fun open source work.

What you’ll be doing:

• Own the design, implementation and optimization of our AI agent workflows and supporting infrastructure, ensuring reliability, scalability and rapid iteration.
• Collaborate closely with the rest of the engineering team on our RAG pipeline, continuously improving response quality, latency and robustness.
• Monitor and optimize system performance and costs, making pragmatic tradeoffs to keep us lean and moving fast.
• Establish best practices for prompt engineering and deployment of new models and workflows.
• Own the design and automation of eval pipelines to continuously measure, benchmark and improve AI agent quality and reliability.

You’re likely a good fit if:

• You are quick, scrappy and first and foremost a hacker/builder - comfortable moving from idea to production in days, not weeks.
• You have experience shipping complex backend and AI/ML features to real users.
• You’ve worked on full stack agent behaviors and have hands-on experience with LLMs, RAG, and agent architectures.
• You have worked in a high-growth, fast-paced environment (ideally another startup) and can drive things forward with relatively little oversight.

We’re based in San Francisco with members of the team distributed across the US and Europe.

If you're interested in moving to SF, we're more than happy to sponsor your visa. We'll work with an immigration attorney to make sure everything goes smoothly.

We offer premium healthcare (medical, dental, etc.), flexible working hours and office space with a beautiful view of the SF marina and Golden Gate bridge.

To apply, reach out with a couple of sentences about you, links to your previous work and what you want to do for us starting next week.Applications without this information are automatically archived.