Responsibilities
- Embed deeply with assigned business function by attending meetings, mapping workflows end-to-end, and learning pain points firsthand before proposing changes.
- Ask whether AI should be used at all and choose the appropriate type of AI (agentic system, generative AI, classical ML, RAG, or simple automation) based on the problem.
- Identify which parts of a workflow are genuinely agent-shaped — multi-step, tool-using, decisioning tasks where autonomy adds value.
- Translate business problems into clear technical designs including architecture diagrams, data flow maps, integration points, tool selection, and build vs. buy vs. integrate decisions.
- Design agentic systems deliberately: decompose tasks, define agent goals, tools, and action space, choose between single-agent and multi-agent orchestration, and specify planning, reasoning, memory/state retention, human escalation, and guardrails.
- Engineer agents for reliability: handle failure modes, retries, tool errors, hallucination recovery, cost and latency budgets, human-in-the-loop checkpoints, and graceful degradation.
- Build evaluation and observability from day one: define task-level success criteria and eval sets, and instrument tracing, logging, and monitoring for measurable behavior in production.
- Manage stakeholders proactively: act as translator between business needs and technical reality, set honest expectations, surface risks early, prevent scope creep, and avoid surprises.
- Support post-handoff sustainability so that systems remain operational and maintainable after moving to the next engagement.
Requirements
- 6+ years of software engineering experience, with at least 3 years building applied AI/agentic solutions in a production environment.
- Demonstrated experience designing, building, and shipping reliable agentic systems to production: tool-using agents that plan, call tools/APIs and MCP servers, and complete multi-step tasks.
- Owned the reliability engineering that keeps agentic systems running, including failure handling, human-in-the-loop control, guardrails, and cost and latency management.
- Experience building internal platforms, SDKs, or tooling adopted by other teams, with design, documentation, and usability that drive real adoption.
- Strong Python skills and deep command of the agentic stack: one or more agentic frameworks (LangChain/LangGraph, LlamaIndex, AutoGen, CrewAI, the OpenAI Agents SDK, or similar), tool/function calling, orchestration, and state/memory management.
- Proficient in prompt and context engineering, RAG architectures, vector databases, LLM APIs, structured outputs, and integrations with internal and third-party systems.
- Able to build AI solutions end-to-end — from problem statement through architecture and design to a working solution without relying on another engineer to execute designs.
- Sound judgment on whether to use AI at all, and which kind to use (agent, RAG, classical ML, or simple automation), including the discipline to say no rather than default to the most sophisticated option.
- Proven ability to work directly with non-technical stakeholders and manage expectations.
- Comfort operating in ambiguous, early-stage environments where you define the problem as much as you solve it, starting from a vague complaint, working back to a crisp technical plan, and knowing when to prototype quickly versus when to build for the long term.
Nice to Have
- Experience designing multi-agent systems, coordinating multiple specialized agents, planner/executor patterns, and agent-to-agent or protocol-based tool interoperability.
- Experience in an embedded, consultative, or cross-functional role — serving another team's goals rather than your own backlog.
- Familiarity with workflow analysis and process mapping — documenting how work actually gets done before proposing changes.
- Experience evaluating and observing agent/LLM systems — building eval sets, defining success criteria, and instrumenting tracing, monitoring, and drift detection using tooling such as Datadog, LangSmith, or Langfuse.
- Experience in media, entertainment, streaming, or consumer technology, with awareness of content workflows, localization pipelines, marketing operations, or rights management.
- Exposure to AI governance and security review processes — knowing what questions IT, legal, and security will ask, including agent-specific risks (tool/permission scope, prompt injection, data handling, autonomous-action safety), and designing with those constraints in mind from the start.
Benefits
- Great compensation package including salary plus performance bonus earning potential, paid annually.
- Flexible time off policies allowing you to take the time you need to be your whole self.
- Generous medical, dental, vision, STD, LTD, and life insurance.
- Health Saving Account (HSA) program.
- Health care and dependent care FSA.
- 401(k) plan, with employer match.
- Employer paid commuter benefit.
- Support program for new parents.
- Pet insurance and some of our offices are pet friendly!
Work Arrangement
Hybrid
Why you will love working at Crunchyroll
- Work with fun, passionate and inspired colleagues.
- Receive a great compensation package including salary plus performance bonus earning potential, paid annually.
- Flexible time off policies allowing you to take the time you need to be your whole self.
- Generous medical, dental, vision, STD, LTD, and life insurance.
- Health Saving Account HSA program.
- Health care and dependent care FSA.
- 401(k) plan, with employer match.
- Employer paid commuter benefit.
- Support program for new parents.
- Pet insurance and some of our offices are pet friendly!
- #LifeAtCrunchyroll #LI-Hybrid
About our Values
- Courage. We believe that when we overcome fear, we enable our best selves.
- Curiosity. We are curious, which is the gateway to empathy, inclusion, and understanding.
- Kaizen. We have a growth mindset committed to constant forward progress.
- Service. We serve our community with humility, enabling joy and belonging for others.
Our commitment to diversity and inclusion
- Our mission of helping people belong reflects our commitment to diversity & inclusion.
- We are an equal opportunity employer and value diversity at Crunchyroll.
- Pursuant to applicable law, we do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.
Additional Information
- Must operate in a hybrid work model.
- Role involves direct collaboration with non-technical stakeholders.
- Candidate must be comfortable in ambiguous, early-stage environments.
- Position requires strong communication and expectation management skills.
- No mention of language requirements, travel, shifts, equipment, clearance, background checks, contract duration, probation, or relocation assistance.