FDE

Kaltura•Remote, NY

2d•Hybrid

About The Position

Kaltura is seeking a Forward-Deployed Engineer (FDE) to join a small team embedded with priority customers. The FDE will own technical delivery from the initial prototype to stable production, building customer-specific capabilities that provide immediate value and can become durable platform capabilities if proven broadly useful. The role involves agent engineering, which combines prompt design, software engineering, and evaluation. The FDE will write behavioral instructions, develop the underlying code, and test both against evaluation and latency requirements, all while embedded with the customer and translating their domain into working, tested artifacts. The FDE's pod will not modify the platform core but will consume and extend shared components from the Foundation team, ensuring all shipped work is a versioned, tested engineering artifact of platform-grade quality. Skills developed for one customer that prove useful across others will be promoted into the foundation. The role emphasizes a fast-paced environment that encourages initiative, with a hybrid work model and flexible mindset to foster creativity. Kaltura believes in hiring people, not just a list of skills, and encourages applications even if not all requirements are met.

Requirements

4+ years in a technical, customer-facing engineering role (Forward Deployed Engineer, Solutions Engineer with production code responsibility, or Software Engineer with consulting/deployment experience).
Ability to write and review production-quality code.
Production experience with LLMs: prompt engineering, agent development (LangChain, LangGraph, or equivalent), RAG pipelines, tool/function calling, evaluation frameworks, and deployment at scale.
Ability to author and evaluate AI skills as engineering artifacts: writing behavioral instructions, writing the code beneath them, designing test scenarios, and measuring behavioral consistency.
Experience building integrations that started as customer-specific and became broadly reusable: wrapping external APIs, webhooks, and tools into governed, contracted interfaces.
Understanding latency across distributed calls.
Strong domain learning ability: quickly absorbing unfamiliar industries to author domain-specific artifacts within weeks.
Ability to conduct discovery and translate domain conversations into engineering requirements.
Clear communication with engineers and non-technical stakeholders.
Ability to serve as the senior technical counterpart for customer teams, conduct architecture reviews, and spot risks early.
Ability to scope work, sequence delivery, and remove blockers.
Making deliberate trade-offs between scope, speed, and quality to protect delivery timelines in fast-moving or ambiguous environments.

Nice To Haves

Experience with MCP servers and agent frameworks: building or consuming them in production, understanding tool registration, contracts, and multi-agent coordination.
Background in speech/NLP pipelines: ASR vocabulary biasing, TTS pronunciation customization, or similar domain adaptation of speech models.
Experience with evaluation and observability tooling: DeepEval, Ragas, Langfuse, Opik, or similar.
Familiarity with real-time system constraints: understanding conversational avatar latency and how latency budgets shape turn-based interactions.
Experience with multi-tenant platforms: tenant isolation, scoped configuration, registry patterns, and ensuring tenant data separation.
Track record of codifying patterns into tools, playbooks, runbooks, and reproducible benchmarks that scale a field engineering function beyond individual heroics.

Responsibilities

Build customer-specific capabilities that deliver immediate value and become durable platform capability when proven broadly useful.
Consume Foundation team's shared components (registry, gateway, evaluation harness, guardrails, memory) and extend them for customers.
Ship versioned, tested engineering artifacts held to platform-grade quality.
Write behavioral instructions, write the code beneath them, and prove both against evaluation and latency cases.
Translate customer domains into working, tested artifacts.
Register skills through the platform registry with mandatory evaluation gates.
Wrap and register customer tools, APIs, and MCP servers with contracts and permissions.
Bring integrations through the Foundation's gateway and validate the full flow meets latency budgets, fixing and contributing back when it doesn't.
Create evaluation suites with ground-truth scenarios and acceptance cases drawn from the customer's domain.
Provide ASR vocabulary biasing and TTS pronunciation lexicons.
Perform ongoing tuning, including knowledge creation, behavior configuration, checkups, and production feedback integration.
Codify patterns into tools, playbooks, runbooks, and reproducible benchmarks that scale a field engineering function.