Senior Technical Product Manager — AI Inference & Software

Positron Corporation; United States; Remote; USD 200,000 - 350,000; Full time

Benefits offered by this job

Health insurance

Life & disability coverage

Remote work setup

Unlimited PTO

13 holidays

401(k) with matching

Equity

Job summary

Positron AI is seeking aTechnical Product Manager to own AI inference planning, translating model and system advances into concrete, well-scoped requirements for the inference software stack. You will bridge engineering, GTM, and ecosystem partners, tracking the frontier and turning insights into engineering tasks.

You will leverage agentic AI daily to refine roadmaps, drive cross-functional collaboration, and shape a high-performance serving and managed-service strategy in a fast-evolving AI

Qualifications

• 10+ years across ML systems or serving-stack engineering with performance trade-offs.
• Deep expertise in transformer internals at operator level and hardware implications.
• Hands-on experience with production inference serving at scale and observability.
• Fluency with open-source inference ecosystems and model deployment cycles.
• Strong skills in performance analysis, benchmarking, and math justification.
• Experience in competitive landscaping of inference providers and stacks.
• Ability to learn quickly across full stack from models to fleet-scale serving.
• Excellent communication and leadership in uncertain environments.
• Daily use of agentic AI for research, analysis, and drafting requirements.

Responsibilities

• Lead all aspects of AI inference and software product planning.
• Write requirements for the inference software stack across models, numerics, and serving features.
• Partner with engineering and GTM to deliver a clear, defensible roadmap.
• Develop scope and feasibility frameworks translating model innovations into engineering tasks.
• Track the model frontier and feed market needs back into the roadmap.
• Engage ecosystem partners to align technology roadmaps with product goals.
• Define software lifecycle, versions, releases, and deprecation policies.
• Ensure thorough internal and customer-facing documentation.
• Automate planning processes using agentic AI.

Skills

ML systems

Inference serving

Transformer internals

Open-source runtimes

Model governance

System performance analysis

Communication

Decision history

Agentic AI workflows

Tools

vLLM

SGLang-class runtimes

Inference runtimes

Job description

Positron AI is seeking aTechnical Product Manager to own AI inference planning, translating model and system advances into concrete, well-scoped requirements for the inference software stack. You will bridge engineering, GTM, and ecosystem partners, tracking the frontier and turning insights into engineering tasks.

You will leverage agentic AI daily to refine roadmaps, drive cross-functional collaboration, and shape a high-performance serving and managed-service strategy in a fast-evolving AI