🚀 We’re hiring an ML Engineer at Pruna AI

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

While much of the AI world focuses on scaling massive foundation models, we aim to level the playing field by making state-of-the-art models accessible, efficient, and production-ready . After years of research in efficient ML, we decided to take impact into our own hands—helping teams maximize performance while minimizing cost and carbon footprint.

🔍 The Role

As an ML Engineer at Pruna AI , you’ll bridge cutting-edge research and real-world deployment.

You’ll identify the most promising AI models from the community and industry, optimize them using advanced efficiency techniques , and deploy them so end users can benefit from state-of-the-art performance without heavy infrastructure costs.

This is a hands-on role combining deep ML expertise with strong engineering and product instincts.

🛠️ What You’ll Do

Model Optimization

• Analyze newly released open-source models and assess optimization impact
• Apply internal and external efficiency methods
• Benchmark performance vs. baselines with minimal quality trade-offs
• Produce clear, actionable reports for go-to-market and communication
• Continuously improve models as hardware and research evolve

Deployment & Delivery

• Package and deploy optimized models to the cloud
• Integrate models into Pruna’s SaaS platform and customer environments
• Collaborate with Software and Research teams on testing, deployment, and monitoring

Customer & Partner Engagement

• Work closely with customers and users of Pruna’s optimized models
• Understand production constraints and iterate quickly based on feedback

🌟 What We’re Looking For

Experience & Background

• B.Sc./M.Sc./Ph.D. in CS, ML, or related fields—or equivalent industry experience
• Strong experience with modern AI models (transformers, diffusion, multimodal)

ML & Engineering Skills

• Strong foundations in deep learning and applied ML
• Expertise in PyTorch and Python
• Experience deploying models to production environments
• Familiarity with Cog, Litserve, vLLM, Docker, and cloud platforms (AWS/GCP/Azure or Replicate/Runpod/Modal)

Nice to Have

• Experience with compression techniques (quantization, pruning, distillation)
• Knowledge of low-level optimization (Triton, CUDA, C++)
• Customer-facing or forward-deployed ML experience

We’d love to hear from you — even if you don’t meet 100% of the requirements.

⚖️ Compensation & Benefits

💸 Top-market salary , based on seniority and location

🌞 Meal vouchers, health & wellness benefits, mobility support

✈️ Travel policy to visit fellow Pruners

🏡 Remote stipend for your home workspace

🛤️ Hiring Process

1. Intro Call (~1h)
2. Foundations Interview (~1h)
3. Take-home Challenge + discussion (2h prep + 1h call)
4. Meet the Team (~1h)

We adapt the process to your needs to ensure equal opportunity for all candidates. Pruna AI is an equal opportunity employer and is committed to building a diverse and inclusive team. We strongly encourage applications from women and from individuals who bring diverse backgrounds, perspectives, and experiences that enrich our research and product development.