AI Professional Services Engineer
About The Position
Kaltura is hiring a hands-on engineer for an AI Professional Services (Forward-Deployed) Engineering pod. The role involves working with a small team embedded with priority enterprise customers and owning technical delivery from initial discovery and prototyping through stable production. The engineer builds customer-specific capabilities that provide immediate operational value and, when broadly useful, become durable platform primitives. The work includes building production skills and agents, automated evaluation suites using ground-truth scenarios and golden datasets, and observability and continuous-tuning capabilities. The role calls for experience with microservices, AI applications, and product development, as well as the ability to understand and design agentic system architecture. Kaltura is a global video technology company with more than 700 employees and offices in New York, London, Singapore, and Tel Aviv. It describes its work environment as diverse, collaborative, fast-paced, and hybrid.
Requirements
- At least 2 years of production software engineering experience.
- Hands-on experience building backend services, distributed systems, and APIs in Python, TypeScript/Node.js, or Go.
- Direct experience building and deploying stateful agent workflows, tool/function calling, structured outputs, context-window optimization, and production RAG pipelines, including hybrid search, semantic chunking, and re-ranking.
- Proven experience providing customer-facing technical ownership as a technical lead with external engineering teams, such as in a Forward-Deployed Engineer, Solutions Engineer with production code ownership, or founding engineer role.
- Ability to conduct architecture reviews and design agentic systems.
- Ability to work in complex, unfamiliar enterprise environments, derive technical requirements from ambiguous business problems, and rapidly design working systems.
- Familiarity with observability and measurement techniques.
Nice To Haves
- Hands-on experience authoring or consuming Model Context Protocol (MCP) servers and clients to standardize agent tool interoperability.
- Background in speech pipelines, including ASR domain vocabulary biasing and TTS pronunciation tuning.
- Experience with multi-tenant architecture, strict tenant isolation, and preventing cross-tenant context leakage.
Responsibilities
- Own technical delivery for priority enterprise customers from initial discovery and prototyping through stable production.
- Build customer-specific capabilities that provide immediate operational value and can become reusable platform primitives when broadly useful.
- Build production skills and agents using an understanding of microservices, AI applications, and product development.
- Create automated evaluation suites, including ground-truth test scenarios, golden datasets, and regression suites measuring semantic correctness, tool-call fidelity, and behavioral stability.
- Apply observability and measurement techniques and support continuous tuning.
- Write, review, and ship production code.
- Act as a technical lead with external engineering teams.
- Conduct architecture reviews and design agentic systems.
- Extract technical requirements from complex enterprise environments and ambiguous business problems, then rapidly design working systems.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
