2 months ago
Cambridge, United KingdomEntry Level / Mid Level
Responsibilities
- Architect, develop, and deploy AI agents and copilots for Roku TV use cases, integrating them with internal systems, tools, and services.
- Own agentic systems end to end from prototyping and architecture through orchestration, evaluation, deployment, observability, and improvement.
- Design single-agent and multi-agent orchestration patterns with handoffs, delegation, and cooperative task execution.
- Build scalable RAG and context pipelines that ground AI systems in evolving data sources and business logic.
- Implement tool-calling, function-calling, and MCP-style integrations so agents can safely interact with surrounding systems.
- Create reusable agent templates, modular components, and paved-path patterns for adoption across teams.
- Establish evaluation, observability, and monitoring for conversation quality, task success, latency, cost, and system performance.
- Build testing pipelines, controlled rollouts, drift detection, and safeguards that improve production readiness and prevent error amplification.
- Prototype and experiment rapidly, then convert successful concepts into durable, scalable software solutions.
- Collaborate with engineering, product, QA, infrastructure, and cross-functional teams to deliver customer and business outcomes.
Requirements
- Bachelor’s or master’s degree in Computer Science, Computer Engineering, Electrical Engineering, Data Science, or a related technical field.
- At least 2 years of experience in software engineering, AI/ML engineering, backend development, or an adjacent domain.
- Strong proficiency in Python and experience with C/C++ or another systems language.
- Hands-on experience with LLM-based systems, including prompt design, retrieval, tool use, memory handling, and agent orchestration.
- Experience building RAG pipelines, agent frameworks, MCP servers or equivalent function-calling architectures, and conversational interfaces.
- Familiarity with cloud platforms, REST APIs, containerization, and modern deployment environments.
- Experience with observability, evaluation, experimentation, and production feedback loops for AI systems.
- Preferred experience with multi-agent frameworks such as LangChain, AutoGen, or Semantic Kernel.
- Preferred experience with video, audio, TV, or edge-device environments and related latency, cost, or hardware constraints.
- Familiarity with PyTorch or TensorFlow, research or paper implementation experience, or practical application of emerging GenAI techniques.
Benefits
- Hybrid work generally Monday through Thursday in the office, with Fridays generally flexible for remote work.
- Healthcare options may include medical, dental, and vision, along with life, accident, disability, commuter, and retirement benefits.
- Global mental health and financial wellness support and resources are available.
- Paid time off is provided according to local leave policies and personal needs.
Categories
About Roku
Roku builds streaming players, Roku-branded TVs and audio gear, and the Roku OS licensed to TV manufacturers. Its platform supports ad-supported and subscription streaming, including The Roku Channel and Roku Originals, and underpins a significant advertising business. Founded in 2002 and headquartered in San Jose, it is a public company trading on NASDAQ under the ticker ROKU.