About this role
Designing and implementing secure, reliable AI-powered tools and platforms using large language models and retrieval-augmented generation occupies the center of daily engineering operations. Engineers in this group integrate these capabilities into core workflows to improve quality, performance, and operational oversight while defining coding and documentation standards for Python-based services.
Building out AI tooling and pipelines with large language models, retrieval-augmented generation, and Model Context Protocol forms the primary technical focus. The team establishes automated quality gates, conducts code reviews, and coordinates cross-functional delivery with system architects, platform teams, UI, product, data, and QA groups. Mentoring engineers, leading onboarding, and translating company strategy into execution roadmaps round out the core responsibilities.
Engineers who succeed here combine deep technical delivery skills with structured architectural judgment and cross-functional leadership. Candidates with a pragmatic approach to problem-solving, strong Python and cloud-native backgrounds, and an affinity for fast-paced media technology environments thrive on this team.
What you will do
- Design and implement secure, reliable AI-powered tools and platforms using large language models and retrieval-augmented generation.
- Architect AI tooling and pipelines utilizing LLMs, RAG, and MCP, including retrieval design, model orchestration, and safety guardrails.
- Define coding and documentation standards for Python-based services and conduct code and design reviews.
- Lead onboarding and mentor team members through structured curricula, shadowing, and educational code reviews.
- Orchestrate cross-functional alignment with system architects, platform, UI, product, data, and QA teams to deliver core features.
- Translate company strategy into an engineering roadmap with clear priorities, success metrics, and delivery commitments.
What you need
- Hold a Bachelor's degree or foreign equivalent in Computer Science or a related field.
- Bring at least 2 years of experience in the position, as a Software Engineer, or in a related occupation.
- Demonstrate at least 1 year of prior work experience building and integrating AI tooling using Agents and Model Context Protocol with adapters, authentication, auditing, and lifecycle management.
- Show at least 1 year of experience developing and evaluating prompts and systems with grounding, citation, hallucination mitigation, red-teaming, and A/B experimentation.
- Possess at least 1 year of experience designing and delivering user interfaces that prioritize clarity, discoverability, and minimal friction.
- Have at least 1 year of experience optimizing performance through latency and throughput tuning, async concurrency patterns, profiling, and device-cloud considerations.
- Demonstrate system design, tradeoff analysis, architectural patterns, and code review experience.
- Bring work experience with Python services, Linux, cloud-native stacks, concurrency, async I/O, and modern networking for AI workloads.
Benefits
- Global access to mental health and financial wellness support and resources
- Healthcare options including medical, dental, and vision
- Life, accident, and disability insurance
- Commuter and retirement options such as 401(k) or pension
- Paid time off in accordance with local leave policies
Skills and tech stack
Questions candidates ask
What is the remote work policy?
Teams generally work in the office Monday through Thursday. Fridays are generally flexible for remote work, and up to one day per week telecommuting may be permitted.
What technology stack will I be working with?
The role involves working with Python services, Linux, cloud-native stacks, large language models, retrieval-augmented generation, and Model Context Protocol. Engineers also handle concurrency, async I/O, and modern networking for AI workloads.
What does the team collaboration look like?
Engineers orchestrate cross-functional alignment with system architects, platform, UI, product, data, and QA to deliver core OS features. The work also involves leading incident triage, mentoring team members, and driving alignment on objectives and risks.
How can I request accommodations during the hiring process?
Applicants requiring reasonable accommodation at any point in the hiring process can direct inquiries to EmployeeRelations@Roku.com. Roku provides reasonable accommodations in accordance with applicable law.