Overview
We're looking for a technically strong Product Manager to join our PhariaAI Inference Team and help shape the future of our advanced inference platform. This role is ideal for someone with product management experience, a deep understanding of AI infrastructure, and a strong grasp of the performance and economics of large language model deployment.
Your Responsibilities
- Shape the product strategy and roadmap for our inference platform in close collaboration with engineering and research, aligning OKRs with business goals and user needs
- Provide clarity on goals and constraints, enabling the team to explore and deliver the best solutions.
- Work closely with engineering to prioritize and deliver high-impact features, ensuring a fast, reliable, and scalable inference stack
- Define clear, actionable requirements and success criteria that balance technical feasibility with user and business impact
- Continuously learn from real-world usage, incorporating performance metrics, user feedback, and experimentation results into iterative improvements
- Stay informed about the latest in inference technologies, optimization techniques, and the broader LLM landscape to inform product direction
- Partner with customer-facing teams to articulate the value and differentiation of our inference capabilities in a fast-moving competitive environment
Your Profile
- Experience in product management for software products, ideally with exposure to developer tools, AI/ML systems, or technical platforms
- Familiarity with modern product discovery and agile delivery practices
- Strong technical curiosity fluency and willingness to learn about AI inference technologies
- Strong communication skills, especially when distilling technical complexity for non-technical audiences
- Strong analytical skills to evaluate market trends and competitive offerings
- A customer-obsessed mindset and the ability to deeply understand user needs—even when those users are internal AI teams
- Ability to thrive in a fast-paced environment and manage multiple priorities
Bonus (but Not Required)
- Basic understanding of inference optimization techniques such as quantization, LoRA adapters, function calling, structured outputs, and batch processing
- Familiarity with the economics of LLM inference, including GPU utilization, token economics, and performance trade-offs
- Exposure to inference engines such as vLLM, SGLang, TGI, or similar technologies
- Experience with retrieval-augmented generation (RAG) pipelines, embeddings, and multi-modal systems
- Understanding of the challenges in long-context handling and advanced sampling methods
- Experience with multi-modal AI systems
What You Can Expect From Us
- Access to a variety of fitness & wellness offerings via Wellhub
- Mental health support through nilo.health
- Substantially subsidized company pension plan for your future security
- Subsidized Germany-wide transportation ticket
- Budget for additional technical equipment
- Regular team events to stay connected
- Flexible working hours for better work-life balance
