Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Applied AI Engineer role.
Rezi rewrites your resume against Level's job description. Free.
Tailor your resume to this Applied AI Engineer role.
Rezi rewrites your resume against Level's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Applied AI Engineer posting at Level — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Applied AI Engineer posting at Level — free, in seconds.
About the Role
Design, build, and ship production agentic systems, providing governance and security guidance for AI designs and usage. Automate Subject Matter Expert (SME) workflows by identifying and replacing manual tasks with AI systems, ensuring SME co-ownership of quality. Make AI features safe by designing for compliance, running safety and bias evaluations, and implementing human-in-the-loop controls. Ensure smooth handoffs of shipped features with documentation and runbooks. Foster a culture of safe AI adoption by creating manageable ecosystems that enable cross-functional teams.
Responsibilities
- Design and build agents and agentic workflows that solve a defined problem end to end.
- Own prompts, tools, retrieval, guardrails, observability, cost and latency budgets, and rollout for agentic systems.
- Provide governance and security guidance surrounding AI designs, strategy, and usage.
- Identify high-leverage operational toil and partner with SMEs to replace meaningful chunks of that work with AI systems.
- Design for relevant compliance frameworks from day one.
- Run safety and bias evaluations before launch and continuously after.
- Build human-in-the-loop and content-filtering controls for AI features.
- Ensure production features leave with documentation, runbooks, an eval harness, and dashboards.
- Foster a culture of safe AI adoption with manageable ecosystems that integrate and enable cross-functional teams.
Requirements
- 7+ years professional experience as an Engineer.
- 1+ years of hands-on experience building agentic systems on at least one modern stack (LangGraph, Anthropic SDK / Claude Agent SDK, OpenAI Agents SDK, Pydantic-AI, Mastra, LlamaIndex, CrewAI, or a homegrown stack).
- Experience building and operating agentic systems in production.
- Strong Python familiarity.
- Familiarity with one typed language for production services (TypeScript, Go, or similar).
- Cloud experience (AWS or GCP).
- Containerized deployment experience.
- Software engineering foundation with several years of production environment experience.
- Track record of leading systems to launch.
- Multiple shipped LLM-powered features in a production environment.
- Practical knowledge of common agentic patterns: ReAct, tool use with structured schemas, prompt chaining, routing, orchestrator-workers, evaluator-optimizer / reflection, and human-in-the-loop.
- Ability to decide when a deterministic workflow is the right answer instead of an autonomous agent.
- Hands-on experience in a production environment with retrieval: chunking, embeddings, hybrid search, re-ranking, metadata filtering, and their failure modes.
- Working knowledge of grounding techniques that anchor generated answers in retrieved evidence.
- Strong prompt-engineering practice: zero-shot, few-shot, and many-shot patterns; example selection and ordering; in-context learning and chain-of-thought.
- Comfort with structured output and validation in production.
- Disciplined evaluation practice; do not rely on subjective review to decide system readiness.
- Experience in standing up local models and creating and testing closed local model solutions.
- Strong written and verbal communication skills.
- Comfort using AI coding tools heavily while owning problem framing, design choices, and verification.
- Advanced retrieval experience (GraphRAG, agentic retrieval, evaluation-driven retrieval tuning, hybrid retrieval at scale) is a plus.
- Direct or transferable experience with safety, privacy, and policy constraints in user-facing AI is a plus.
- K-12 or other regulated-domain experience is a strong plus.
- Experience with prompt-optimization frameworks (DSPy, TEXTGRAD, AdalFlow) where they paid off in production is a plus.
- A public repo, package, gist, or technical write-up of meaningful AI work, or a representative project is a plus.
- Open-source contributions to AI tooling (frameworks, agents, evals, MCP servers) is a plus.
Skills
- Agentic systems
- LangGraph
- Anthropic SDK / Claude Agent SDK
- OpenAI Agents SDK
- Pydantic-AI
- Mastra
- LlamaIndex
- CrewAI
- Python
- TypeScript
- Go
- AWS
- GCP
- Containerized deployment
- LLM-powered features
- ReAct
- Tool use with structured schemas
- Prompt chaining
- Routing
- Orchestrator-workers
- Evaluator-optimizer / reflection
- Human-in-the-loop
- Retrieval
- Chunking
- Embeddings
- Hybrid search
- Re-ranking
- Metadata filtering
- Grounding techniques
- Prompt engineering
- Zero-shot patterns
- Few-shot patterns
- Many-shot patterns
- Example selection
- Example ordering
- In-context learning
- Chain-of-thought
- Structured output
- Validation
- Evaluation
- Local models
- AI coding tools
- GraphRAG
- Agentic retrieval
- Evaluation-driven retrieval tuning
- Hybrid retrieval at scale
- Safety
- Privacy
- Policy constraints
- Prompt-optimization frameworks
- DSPy
- TEXTGRAD
- AdalFlow
- Open-source contributions
Experience Level
- 7+ years professional experience
- 1+ years hands-on experience building agentic systems