Senior Product Manager - LLM Inference

present of AI; United Kingdom; Remote; GBP 90,000 - 150,000; Full time

Job summary

Runware is seeking a product leader to own the strategy, roadmap and commercial results for its LLM inference product. You will shape the model catalog, API capabilities and production readiness, working with engineers to balance quality, latency, throughput and cost.

You should have hands-on experience with API testing, usage data analysis and making trade-offs that affect developer experience and unit economics. This is a hands-on, cross-functional role.

Qualifications

• Experience owning API or developer-facing products.
• Understanding of LLM inference, latency, and cost trade-offs.
• Ability to work with engineers on production readiness.

Responsibilities

• Own strategy, roadmap and commercial results for an LLM inference product.
• Balance model quality, latency, throughput and cost in prioritization.
• Collaborate with engineering and cross-functional teams.

Skills

API product ownership

LLM inference knowledge

Job description

This role owns the strategy, roadmap and commercial results for an LLM inference product, covering the model catalog, API capabilities and production readiness. A strong candidate has led developer facing or API products end to end and can weigh model quality, latency, throughput and cost when setting priorities. Hands on comfort with testing APIs, reading usage data and working through technical trade offs with engineers matters more than formal titles.

How it fits the AI era

The product itself is AI infrastructure, so the work is about making model serving fast, reliable and affordable for teams building on top of it. AI tools speed up parts of discovery, prototyping and analysis, but judgment about which models to offer, what developers actually need and where the unit economics hold stays with the person in the role. Customer conversations and cross team alignment remain human work.

How it builds AI experience

The role builds direct experience with production LLM serving, model evaluation and the trade offs around latency, context length and token cost. It also offers exposure to usage based pricing and capacity planning for dedicated inference. Someone preparing for this could study how serving frameworks and API compatibility work and practice benchmarking models on realistic workloads.

Worth showing

• API product ownership
• LLM inference knowledge

This is our own read, written from the employer's posting and the company's Spotlight. The employer's posting is the source of truth for the role.

About Runware

High-performance inference platform providing serverless and dedicated GPU infrastructure across thousands of machine learning models.