🧠

AI Systems Engineer, Retrieval-Augmented Generation (RAG)

🧠 AI Systems Engineer, Retrieval-Augmented Generation (RAG)

This role is remote but requires availability during most US working hours.

OVERVIEW

At Primer, we are building the future of B2B marketing by unlocking the potential of data-driven decisions. We aim to break through industry norms with our advanced generative AI solutions. As an AI Systems Engineer specializing in Retrieval-Augmented Generation (RAG), you’ll take ownership of designing and optimizing systems that seamlessly integrate external data into generative models, driving real-time, personalized insights for our users.

We are a small and dedicated team (~20 people) distributed across the globe, passionate about making enterprise-level technology accessible to marketing teams. If you thrive in a high-growth environment where you’ll work on cutting-edge AI systems and solve complex data challenges, then Primer is the place for you!

Your Mission

Your mission as an AI Systems Engineer, RAG, is to revolutionize how data is accessed and used by go-to-market teams. You’ll be responsible for the entire data lifecycle, from real-time retrieval to seamless integration with generative models, helping build scalable, fault-tolerant systems that deliver high-quality outputs with minimal latency. You'll collaborate across teams to ensure our RAG systems meet the demands of a fast-moving, high-volume data environment.

What you’ll do

  • Design & Optimize RAG Systems: Architect and refine systems that integrate retrieved data with generative AI models to produce valuable insights in real-time.
  • Manage Data Pipelines: Build and maintain large-scale data pipelines, ensuring stable, low-latency retrieval of structured and unstructured data.
  • API Integration: Leverage your expertise in API integrations, particularly for retrieval tasks, to ensure seamless data flow across external and internal systems.
  • Data Modeling & Databases: Optimize columnar and vector databases (e.g., ClickHouse, Pinecone) for efficient data retrieval in both batch and real-time settings.
  • Collaboration: Work closely with product and engineering teams to ensure the successful delivery of projects, meeting both performance and scalability goals.

What you’ll need

  • 5+ years of experience in software development, ideally in fast-paced, high-growth tech environments.
  • Proven experience in building and optimizing Retrieval-Augmented Generation (RAG) systems, including real-time and batch prompting mechanisms.
  • Expertise in data retrieval and database management, with hands-on experience with columnar databases (e.g., ClickHouse) and vector databases (e.g., Pinecone).
  • Familiarity with machine learning workflows, especially supporting retrieval-based and generative models.
  • Strong understanding of Docker and at least 1+ year of experience with Kubernetes for scalable backend services.
  • Experience with cloud platforms such as AWS, GCP, or Azure.
  • Bonus: Experience with Node.js, TypeScript, BullMq, or other message queues (RabbitMq, ActiveMq, or AWS SQS).

You’ll succeed by having

  • Proactive and honest communication.
  • Experience working in distributed teams, using asynchronous ceremonies.
  • Pleasure working in areas outside of your comfort zone.
  • Strong communication and interpersonal skills
  • Ability to hold yourself and the team to high standards

What’s in it for you?

  • Be part of a different sort of unicorn: an early stage startup focused on profitability with demonstrated, consistent revenue growth (20.1% MoM growth in 2021) that also provides a supportive environment for working families. Many of us have young kids and we prioritize work/life balance.
  • Feel trusted. Our team is fully distributed, supports flexible schedules, and we spend 90% of our time outside of meetings. Fridays are free of meetings. We value outcomes, not face time.
  • We invest in our team and catapult careers. We hope you’ll stay at Primer for a long time, but we’ll help you achieve your goals no matter what. Many people have gone on to top-tiered companies like WhatsApp, Facebook, and Tesla beyond working with our leadership team.
  • We are proud to have attracted a diverse team from all around the world. Our current team is based in the United States, Bosnia, Georgia, Pakistan, India, and Turkey. 50% of our product/engineering team is women.
  • Our engineering ceremonies and technology are world-class, putting engineers in the driver’s seat, and emphasize on transparency.
  • Our founders have a proven track record inside of startups (Y Combinator, Wheelhouse, Modsy, Eden) as well as decades of industry experience from places like BlackRock and Dropbox.
  • Our culture is high-achieving, genuinely kind, and collaborative.

BENEFITS (VARIES BY LOCATION)

  • Fully distributed team and flexible, remote work.
  • Required 5 weeks paid time off.
  • Retirement planning (401k)
  • Generous parental and family leave.
  • Comprehensive health plans.
  • New equipment and office stipend.
  • Support for personal and professional development outside of work.
  • Annual team offsite.
  • Diverse and fun team.

What is the interview process like?

We pride ourselves on being respectful of your time. Our interview process starts with an introductory call with one of our founders or Technical Lead (30 minutes), followed by a deep dive with our Data & Integrations team lead, then a half-day session to meet our team. We typically provide a decision within 24-48 hours from the last meeting and aim to conclude the whole process within a week, provided that it works with your schedule.

What do I do now?

If this sounds like an interesting opportunity, please apply by email at careers@sayprimer.com, and include your LinkedIn profile, CV, Github repos, or anything else that you think might give us a good sense of who you are.