Senior Technical Product Manager – Agent Runtime

Jobtailor; Amsterdam; On-site; EUR 90,000 - 130,000; Full time

Job summary

Jobtailor is seeking a Product Manager for AI platform produts to own agent runtimes, architecting orchestration, memory management, and retrieval strategies. You will define non-functional requirements and lead evals to ensure accuracy and reliability at scale, while guiding model strategy and provider decisions.

You will stay ahead of frontier models and contribute market intelligence. The ideal candidate has 4+ years in product management, with strong background in distributed systems,

Qualifications

• 4+ years in product management, with 2+ years on technical/platform products (APIs, infrastructure, ML systems, or developer tools)
• Deep understanding of LLM-based systems and agent architectures: prompting, tool use, planning, multi-step agent loops, context and memory, multi-agent systems - with enough grasp of retrieval/vector search to judge when it's the right tool
• Background in distributed systems or infrastructure - you understand how runtimes behave under scale and how a change ripples across the stack
• Treats non-functional requirements as a first-class product surface: latency, reliability, scalability, cost, observability
• Hands-on experience creating and running evals that measure and improve agent accuracy and reliability at scale
• Fluency in model operations: model selection and swaps, provider trade-offs, token cost/performance optimization
• Can write technical specs that engineers review for feasibility (not correctness) and prototype with code to validate hypotheses; comfortable with architecture trade-offs (latency vs. accuracy, cost vs. capability)

Responsibilities

• Own the agent runtime architecture.
• Provide technical direction for our agent runtimes: agent orchestration and multi-step loops, context and memory management, retrieval strategy, tool execution and orchestration, model routing and fallbacks, guardrails, caching, streaming, and concurrency.
• Define and own the non-functional requirements of the platform including how well the platform runs: latency, throughput, reliability, graceful degradation, scalability under concurrent agent load, token-cost economics, security, and observability/telemetry.
• Own the creation and running of product evals that prove our agents are accurate and reliable.
• Oversee the model strategy including model selection, swaps, and provider decisions; cost/performance trade-offs; staying current as frontier models move.
• Track market intelligence and provide thought leadership on agentic systems to differentiate the company.

Skills

Agent architectures

LLM systems

Tool use

Multi-step loops

Context memory

Retrieval vector search

Distributed systems

Observability

Eval automation

Model operations

Job description

• Own the agent runtime architecture.
• Provide technical direction for our agent runtimes: agent orchestration and multi-step loops, context and memory management, retrieval strategy, tool execution and orchestration, model routing and fallbacks, guardrails, caching, streaming, and concurrency.
• Define and own the non-functional requirements of the platform including how well the platform runs: latency, throughput, reliability, graceful degradation, scalability under concurrent agent load, token-cost economics, security, and observability/telemetry.
• Own the creation and running of product evals that prove our agents are accurate and reliable.
• Oversee the model strategy including model selection, swaps, and provider decisions; cost/performance trade-offs; staying current as frontier models move.
• Track market intelligence and provide thought leadership on agentic systems to differentiate the company.

Requirements

• 4+ years in product management, with 2+ years on technical/platform products (APIs, infrastructure, ML systems, or developer tools)
• Deep understanding of LLM-based systems and agent architectures: prompting, tool use, planning, multi-step agent loops, context and memory, multi-agent systems - with enough grasp of retrieval/vector search to judge when it's the right tool
• Background in distributed systems or infrastructure - you understand how runtimes behave under scale and how a change ripples across the stack
• Treats non-functional requirements as a first-class product surface: latency, reliability, scalability, cost, observability
• Hands-on experience creating and running evals that measure and improve agent accuracy and reliability at scale
• Fluency in model operations: model selection and swaps, provider trade-offs, token cost/performance optimization
• Can write technical specs that engineers review for feasibility (not correctness) and prototype with code to validate hypotheses; comfortable with architecture trade-offs (latency vs. accuracy, cost vs. capability)