👋 About us

At Pruna, we’re on a mission to make AI more efficient to build a better future.

While the focus of Foundational model Labs is scaling up, we aim to level the playing field by building AI models that are as accessible as possible.

After years of research on efficient ML, we decided that the best way to spread our impact was to take it into our own hands. Each of us cares deeply about empowering people to maximize their impact while minimizing their carbon footprint.

🔍 Role Description

As an ML Engineer at Pruna AI, you will bridge the gap between cutting-edge research and real-world application. Your mission is to identify the most promising AI models released by the community and industry, apply a combination of internal and external efficiency methods and to make them more efficient, and deploy them to be used by end users.

You’ll be at the forefront of operationalizing our research, ensuring that users can benefit from state-of-the-art models without the heavy costs of deployment. This is a hands-on role combining deep ML expertise with practical engineering skills.

What you’ll do:

• Model Optimization

  • Analyse newly released open source models and identify the impact of optimising and deploying this model.

  • Apply a combination of internal and external efficiency methods to make them more efficient.

  • Benchmark performance vs. baseline models and ensure minimal accuracy/performance trade-offs.

  • Generate clear reports that translate technical results into actionable insights for communication and go-to-market.

  • Continuously improve deployed models as research and hardware evolve.

• Deployment & Delivery

  • Package optimized models for deployment on the cloud.

  • Ensure smooth integration into Pruna’s SaaS platform and customer environments.

  • Collaborate with the Software team to scale testing, deployment, and monitoring.

  • Collaborate closely with the Research team to help in identifying and applying promising algorithms as well as giving feedback to what can improve current algorithms.

• Customer & Partner Engagement

  • You will work closely with customers and users of our Optimised Models. Whether it is to identify the most promising models or to understand the exact specifications that are required.

  • You will have a constant contact with users in order to be able to quickly iterate and improve our models to best fit the industry and production use cases.

🌟 Your Skills

We would love to see:

Educational background or Experience

• B.Sc., M.Sc./Ph.D. in Computer Science, Machine Learning, or related fields—or equivalent industry experience.

• Exceptional performance academically.

• Demonstrated experience working with modern AI models (e.g., transformers, diffusion, multimodal architectures,…).

Machine Learning Expertise

• Strong foundations in deep learning and applied ML.

• Expertise in PyTorch and Python.

• Familiarity with model deployment workflows (Cog, Litserve, vLLM, etc.).

Engineering & Deployment

• Experience taking ML models from research to production in real-world environments.

• Understanding of performance benchmarking, profiling, and hardware-aware optimization.

• Comfort with neo cloud platforms (Replicate/Runpod/Modal), or legacy clouds (AWS/Azure/GCP) and containerization (Cog, Docker…).

Evaluation Skills

• Strong understanding of benchmarking tools and frameworks for both quality and efficiency.

• Experience translating evaluation metrics into actionable engineering trade-offs.

Personal Attributes

• Strong sense of ownership and accountability.

• Ability to thrive in ambiguous, fast-moving environments.

• Clear communication skills to bridge research and customer needs.

• Passion for making AI both impactful and sustainable.

Bonus Points

• Experience with compression methods (quantization, pruning, distillation, compilation).

• Knowledge of lower-level optimization frameworks (Triton, CUDA, C++).

• Prior experience in forward-deployed engineering or customer-facing ML roles.

⚖️ Expected Salary

💸 Salary: We pay top market rates based on seniority and location, leveraging publicly available data that we share with you during the process.

🌞 Benefits: Meal vouchers, health & wellness solutions, mobility, travel policy to visit fellow Pruners and a remote stipend for your home workspace.

🛤️  Recruitment process

The recruitment process consists of 4 interviews to check the expectations, technical skills and team/culture fit of the candidate.

1. Intro Call - We have a chat to get to know you, discuss your expectations, and give a feeling of who we are. [~1 hour call]

2. Foundations - We test the foundational knowledge that are important for the role you applied for (e.g. problem solving, coding). [~1 hour call]

3. Challenge - Depending on the role you applied for, we will dive together into a task that is representative of the work that you would be doing at Pruna AI. [~2/3 hours preparation + ~1 hour call]

4. Meet the team - You will have the chance to meet the team and get to know better the everyday life at Pruna AI. [~1 hour call]

Accessibility note: To ensure that everybody who is interested in joining Pruna AI has equal opportunity and ability to start that journey, we have made sure our hiring process is efficient, flexible, and accessible. From the application to interviews, our team will adapt to your needs and what works best to help you show your best.

💜 Our Values

We care deeply about the organization we are growing to achieve our goal of making AI accessible and sustainable. There's many ways we could manage our people and work, and it will evolve over time, however we wanted to share the following main aspirations we want to uphold:

🧠  Decide Wisely

Make rational, customer-focused decisions based on collected insights and experiences.

🤝  Trust by Default

Assume good intentions, communicate transparently and precisely, and create a safe space for collaborating.

🌍  Foster Inclusion

Build an enjoyable and supportive workplace that values integrity, personal growth, diverse backgrounds and perspectives. Read our Code of Conduct for more info :)

🌱  Grow Together

Provide actionable feedback and credit to strengthen teamwork and collaboration.

🚀  Learn Relentlessly

Embrace adaptability in a fast-moving landscape to drive innovation and efficiency.