Senior Product Manager - LLM Inference

We're looking for a Senior Product Manager — LLM Inference to own the strategy, roadmap, and commercial success of Runware's LLM inference offering, spanning our on-demand Model API and dedicated inference solutions.

This is a hands-on senior individual contributor role with end-to-end ownership of the customer-facing LLM product — from initial model discovery and API integration to production adoption, scaling, and enterprise expansion.

You'll work at the intersection of developer experience, LLM capabilities, inference performance, and unit economics, identifying where Runware can deliver the most value and translating customer needs into a focused, commercially sustainable product roadmap.

You'll partner closely with Engineering, Design, Security, and go-to-market teams, as well as our Serverless & Compute Product Manager, who owns the underlying compute platform. Together, you'll align on shared infrastructure priorities and capacity requirements while driving the success of the LLM offering.

Explore our LLM inference platform: https://runware.ai/llm-api
What you’ll do

• Own the LLM inference product strategy and roadmap. Define priorities across model availability, API capabilities, production readiness, and customer adoption, balancing developer needs, technical feasibility, business impact, and unit economics.
• Drive customer discovery and product-market fit. Work directly with developers, AI teams, and technical decision-makers to understand production workloads, evaluate competing solutions, identify adoption barriers, and translate market insights into product decisions.
• Own the model catalog and lifecycle. Guide model discovery, evaluation, launches, and deprecations across open-weight, proprietary, and custom or fine-tuned models. Partner with Engineering and Partnerships on model selection, serving, and routing decisions.
• Shape the developer experience and API capabilities. Make it easy for customers to evaluate, integrate, migrate, and scale LLM workloads through API compatibility, SDKs, documentation, and capabilities such as streaming, tool calling, structured outputs, caching, and batch inference. Support compatibility with OpenAI Chat Completions and Anthropic Messages formats.
• Define production inference requirements. Partner with Engineering on performance, reliability, and cost trade-offs, including latency, time to first token, throughput, concurrency, availability, and serving efficiency. Translate customer workloads into requirements for dedicated capacity, rate limits, routing, fallbacks, and observability.
• Drive adoption and commercial growth. Partner with Sales, Marketing, and Partnerships on product positioning, pricing, packaging, and technical evaluations. Support customer progression from self-service usage to sustained production workloads and dedicated inference commitments.
• Translate enterprise needs into scalable product capabilities. Work with Engineering and Security to define requirements for data residency, retention controls, service commitments, and other production-critical capabilities.
• Stay hands-on throughout product delivery. Write clear requirements, prototype solutions, test APIs, reproduce customer issues, and work closely with engineers to resolve technical constraints and deliver high-quality releases.
• Own product performance and business outcomes. Track activation, production usage, retention, expansion, revenue, gross margin, and service quality. Use customer feedback and product data to continuously refine priorities and measure impact.

• Proven product ownership in a technical, developer-facing environment. Experience leading API products, developer platforms, AI infrastructure, or similar technically complex offerings from strategy and development through launch, adoption, and commercial growth.
• Strong understanding of production LLM inference. Ability to evaluate model capabilities and serving trade-offs, including output quality, context length, token consumption, latency, throughput, reliability, and cost, and translate them into practical product decisions.
• Deep understanding of developer experience and API products. Familiarity with developer workflows from initial integration to production scale, including API design, compatibility, migration, SDKs, documentation, and differences in model capabilities.
• Strong commercial and product judgment. Ability to balance customer requirements, technical constraints, market opportunities, pricing considerations, and unit economics when setting product priorities.
• Experience working directly with technical customers. Proven ability to lead customer discovery, engage with developers and technical decision-makers, assess production use cases, and distinguish recurring market needs from isolated requests.
• Hands-on technical aptitude. Comfortable testing APIs, exploring product behavior, analyzing usage data, building prototypes, and discussing implementation trade-offs with engineers.
• Strong execution and cross-functional leadership. Ability to navigate ambiguity, communicate decisions clearly, align stakeholders, and take accountability for outcomes from initial discovery through delivery and measurable results.

Strong Differentiators

• Direct experience building or scaling an LLM inference API, model-serving platform, or AI infrastructure product.
• Knowledge of GPU inference and model-serving technologies, including batching, quantization, KV caching, capacity planning, and frameworks such as vLLM, SGLang, or TensorRT-LLM.
• Experience with LLM evaluation, benchmarking, and production applications, such as AI agents, coding assistants, and retrieval-augmented generation systems.
• Experience with usage-based pricing, token metering, billing systems, inference unit economics, or dedicated capacity commitments.
• Familiarity with enterprise requirements around data security, residency, observability, and service reliability.
• Previous hands-on experience in software engineering, machine learning engineering, infrastructure, or developer tooling.

We’re a remote-first collective, meeting in person twice a year to plan, brainstorm, celebrate wins, and enjoy some face-to-face time. We have core hours for cooperative working and calls, but outside of that your calendar is yours. Work the hours that let you perform at your peak while also building a healthy life.

Our release cycles are fast and intense, but they’re followed by real downtime. After big pushes we expect the team to unplug, recharge, and come back ready & stronger than ever for the next leap.

• Generous paid time off – vacation, sick days, public holidays
• Meaningful stock options – share in the upside you create
• Flexible hours – own your schedule outside core collaboration blocks
• Family leave – paid maternity, paternity, and caregiver time
• Company retreats – twice-yearly gatherings in inspiring locations