The ad says“Familiarity with A2A protocols and long-running, durable workflows”
The ad says“Deep experience with LLM APIs such as Anthropic or OpenAI, including prompt engineering and tool use/function calling”
The ad says“This is a high-impact individual contributor role at the intersection of LLM infrastructure, API design, production reliability, and developer enablement”
The ad says“Experience building automated test and evaluation suites for LLM-based systems, including golden scenarios, regression detection, and quality gates in CI/CD”
The ad says“Strong Go (Golang) engineering skills; backend systems are Go-first. Proficiency in Python and SQL is also expected”
The ad says“Open-weights model experience such as Llama or Mistral”
The ad says“This is a high-impact individual contributor role at the intersection of LLM infrastructure, API design, production reliability, and developer enablement”
The ad says“Fine-tuning experience such as LoRA or PEFT”
The ad says“Experience with MCP or equivalent tool-layer abstractions for exposing platform capabilities to AI agents, or for building agents that consume them”
The ad says“Open-weights model experience such as Llama or Mistral”
The ad says“Multi-tenant system design: experience implementing rate limiting, caller attribution, tenant isolation, and external support surfaces for shared production APIs”
The ad says“Deep experience with LLM APIs such as Anthropic or OpenAI, including prompt engineering and tool use/function calling”
The ad says“Fine-tuning experience such as LoRA or PEFT”
The ad says“Deep experience with LLM APIs such as Anthropic or OpenAI, including prompt engineering and tool use/function calling”
The ad says“Strong Go (Golang) engineering skills; backend systems are Go-first. Proficiency in Python and SQL is also expected”
The ad says“Familiarity with Rust”
The ad says“Strong Go (Golang) engineering skills; backend systems are Go-first. Proficiency in Python and SQL is also expected”
The Principal AI Infrastructure Engineer will serve as a technical cornerstone of VideoAmp’s AI Infra team, driving the design and execution of agentic workflow systems that bridge VideoAmp’s platform APIs and AI-powered customer experiences
This is a high-impact individual contributor role at the intersection of LLM infrastructure, API design, production reliability, and developer enablement
You will architect and own production-critical systems serving live customers, operate in a rigorous evaluation-driven culture, and help VideoAmp safely scale its agentic platform to direct enterprise consumers
The AI Infrastructure team owns the production-critical stack that powers VideoAmp’s agentic experiences. At the core, agent runtimes leverage MCP tools and specialized agents to deliver end to end experiences and workflows
A comprehensive observability layer acts as the basis for replay, analysis, and supervised learning. Quality is ensured via an evaluation framework that provides automated workflow testing with quality gates wired into release pipelines
The team is actively building the next phases of the platform, including A2A APIs, multi-agent delegation, durable long-running agent task runtimes, reusable skills, workflows, agent memory, and agent knowledge
You will have the opportunity to shape how these systems scale, how they interoperate, and how the next generation of VideoAmp’s agentic platform is designed from the ground up
Own multi-tenant tool layers. Design and implement multi-tenant isolation, rate limiting, and caller-attribution systems as direct enterprise customers use MCP tools
Extend A2A interfaces and experiences. Enable customer and internal agents to invoke other agents in support of new initiatives
Build and own durable agent runtimes, including long-running execution, task lifecycle management, and failure recovery
Lead evaluation-driven development. Design golden scenario suites, automated CI/CD evaluation pipelines, and regression detection across all workflows. Evaluation is a parallel engineering workstream, not an afterthought
Implement progressive discovery strategies for context, tools, agents, and skills, using deferred loading, search, categorization, and semantic filtering
Design the agent harness and orchestration loop, leveraging isolated context, shared memory, and multi-agent coordination
Drive new agentic capabilities from design to launch for customer experiences, owning production rollouts
Participate in on-call rotation for customer-facing production systems; contribute to incident response, postmortems, and reliability improvements. This team practices full-lifecycle ownership
Partner with internal engineering teams to negotiate and promote API-first designs that serve both programmatic and agentic consumers
Contribute to multi-provider LLM abstraction layers, ensuring flexibility among LLM providers
Facilitate AI office hours and cross-team enablement, serving as the internal expert on LLM tooling, agentic patterns, and tool configuration for teams across VideoAmp engineering
Author, review, and drive clear technical requirements documentation for new solutions: design docs, architecture diagrams, and postmortems
Preferred experience
7+ years of software engineering experience, with 1+ years in AI/ML infrastructure, LLM platform engineering, or agentic system development
Familiarity with A2A protocols and long-running, durable workflows
Multi-tenant system design: experience implementing rate limiting, caller attribution, tenant isolation, and external support surfaces for shared production APIs
Deep experience with LLM APIs such as Anthropic or OpenAI, including prompt engineering and tool use/function calling
Track record of working across engineering, product, and operations teams to drive alignment and rollout of shared infrastructure and capabilities
Production API design and operations: strong background in resource-based API design and experience building or consuming developer-facing platform APIs at scale, including on-call and incident response
Strong Go (Golang) engineering skills; backend systems are Go-first. Proficiency in Python and SQL is also expected
Ability to produce design documents, postmortems, and system diagrams that create shared understanding across technical and non-technical stakeholders
Experience with MCP or equivalent tool-layer abstractions for exposing platform capabilities to AI agents, or for building agents that consume them
Experience building automated test and evaluation suites for LLM-based systems, including golden scenarios, regression detection, and quality gates in CI/CD
Practical experience designing agent loops for production systems, including context and state management across turns, prefix caching for latency and cost, and coordinating multi-step task execution
Fine-tuning experience such as LoRA or PEFT
AdTech or media measurement familiarity, including linear TV, OTT, CTV, and digital video
Open-weights model experience such as Llama or Mistral
