Technical Product Manager, AI Inference & Software

Positron Corporation

3d • $200,000 - $350,000 • Remote

About The Position

Positron AI is seeking a Technical Product Manager to lead the end-to-end technical product planning for AI inference and software. This role involves translating the future direction of models and inference systems into detailed requirements for the inference software stack, covering model coverage, numerics, inference-engine features, serving-stack capabilities, and managed services. It's a deeply technical planning position at the intersection of engineering, go-to-market, and the inference ecosystem. The ideal candidate will continuously track the model frontier, convert these advancements into engineering requests proactively, and act as a liaison between engineering, GTM teams, and ecosystem partners. Daily use of agentic AI for planning functions is expected.

Requirements

• 10+ years of experience in ML systems, inference infrastructure, or serving-stack engineering, with direct ownership of performance or architecture trade-offs.
• Deep expertise in transformer internals at the operator level, including attention variants, MoE routing, KV-cache mechanics, and quantization formats along with their hardware implications.
• Hands-on experience with production inference serving at scale, covering multi-tenancy, latency SLAs (TTFT, TPOT), batching and scheduling, disaggregated serving, KV-cache management, and observability.
• Working fluency in the open-source inference ecosystem, including vLLM and SGLang-class runtimes, kernels, model ingestion, and practical model release, quantization, and adoption.
• Strong performance analysis skills for models and systems, including utilization reasoning, tokens per dollar and tokens per watt arithmetic, and benchmark design, with the ability to personally build and defend the math.
• Demonstrated experience in competitive landscaping and analysis of inference providers and serving stacks, gained at a model lab, an inference API provider, or an AI hardware company.
• Proven ability to learn quickly and span the full stack, from model-architecture details to fleet-scale serving systems, while staying current with the model and inference landscape.
• Excellent communication and interpersonal skills, with comfort navigating uncertainty and driving socialization of ideas and decisions.
• Confidence being the most technically grounded person in a GTM room and the most market-aware person in an engineering room.
• A strong instinct for owning decision history, serving as the documented answer to 'why did we choose X,' including with executive leadership.
• Daily, hands-on use of agentic AI in real technical work, building and running agent workflows for research, analysis, and requirements drafting, with the judgment to verify and own everything the agents produce.

Nice To Haves

• Prior experience at an AI hardware or custom silicon company, with exposure to bringing a new accelerator platform to market.
• Direct contribution to or close engagement with open-source inference runtimes or serving projects.
• Experience defining and operating a managed inference service, including model catalog and deprecation policy.
• A track record of building internal automation or agentic workflows that measurably improved a planning or research function.

Responsibilities

• Serve as the leader for all aspects of AI inference and software technical product planning.
• Write requirements for the inference software stack, including model coverage, numerics, inference-engine features and modes, serving-stack features and modes, and managed-service capabilities.
• Partner with engineering and GTM to build and communicate a clear, defensible roadmap.
• Create scope and feasibility frameworks to translate model and inference-system innovations into tangible engineering requests.
• Keep planning ahead of model and inference system evolution by tracking the model frontier and converting advancements into requirements before customer escalations occur.
• Work closely with GTM teams to understand customer and market needs and integrate them into the roadmap.
• Create competitive briefings on inference providers, serving stacks, and adjacent hardware platforms.
• Engage with key ecosystem partners (model labs, open-source runtimes, serving and orchestration partners) to understand their technology roadmaps.
• Define and manage the software product lifecycle, including versions, release trains, feature modes, model catalog, and deprecation policy.
• Ensure software products are well-documented for internal and customer-facing audiences.
• Streamline and automate the product planning process using agentic AI.

Benefits

• Fully company-paid medical, dental, and vision insurance for you and your dependents
• Company-paid life and disability coverage, with voluntary options to add more
• Supplemental hospital, critical illness, and accident coverage available
• Unlimited paid time off
• 13 paid company holidays
• Remote-first culture with a company-provided computer and home office setup
• Competitive salary and equity
• 401(k) with company matching, eligible from day one
• Visa Support (H-1B visa transfers for eligible candidates)

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed