Applied AI Engineer

Level • Austin, TX

10d

About The Position

The Applied AI Engineer designs, builds, and operates production agentic systems and AI workflows that solve defined problems end to end. The role owns prompts, tools, retrieval, guardrails, observability, cost and latency budgets, and rollout, and provides governance and security guidance for AI design, strategy, and usage.

The engineer partners with subject-matter experts (SMEs) to identify high-impact operational work that can be automated, define success criteria, validate outputs, and replace meaningful portions of workflows with trusted AI systems. SMEs are involved as co-owners of quality from project inception.

AI features are treated as regulated products. The role designs for relevant compliance frameworks, conducts safety and bias evaluations before launch and on an ongoing basis, and builds appropriate human-in-the-loop and content-filtering controls. Shipped production features should include documentation, runbooks, evaluation harnesses, and dashboards.

The role also helps teams adopt AI safely by fostering manageable ecosystems that enable cross-functional teams to create and improve their own workflows and automations.

Requirements

• At least 7 years of professional engineering experience.
• At least 1 year of hands-on experience building agentic systems using a modern framework or a homegrown stack.
• Experience building and operating agentic systems in production.
• Strong familiarity with Python and a typed language used for production services, such as TypeScript or Go.
• Cloud experience with AWS or GCP and containerized deployment experience.
• Several years of production-environment experience and a track record of leading systems to launch.
• Multiple LLM-powered features shipped in production, with concrete examples of failures, fixes, and lessons learned.
• Practical knowledge of agentic patterns including ReAct, structured-schema tool use, prompt chaining, routing, orchestrator-workers, evaluator-optimizer or reflection, and human-in-the-loop.
• Ability to determine when a deterministic workflow is preferable to an autonomous agent.
• Production experience with retrieval, including chunking, embeddings, hybrid search, re-ranking, metadata filtering, and understanding their failure modes.
• Working knowledge of grounding generated answers in retrieved evidence, including citation and quote extraction, faithfulness and refusal evaluations, and post-hoc consistency checks.
• Strong prompt-engineering practice, including zero-shot, few-shot, and many-shot patterns; example selection and ordering; in-context learning; and chain-of-thought.
• Experience with structured output and validation in production using provider-native structured outputs, Instructor, Pydantic-AI, Outlines, or a comparable approach.
• Disciplined evaluation practice; readiness decisions are not based on subjective review alone.
• Experience standing up local models and creating and testing closed local-model solutions.
• Strong written and verbal communication, including explaining architectural trade-offs to executives and junior engineers.
• Comfort using AI coding tools extensively while retaining ownership of problem framing, design decisions, and verification.

Nice To Haves

• Advanced retrieval experience, such as GraphRAG, agentic retrieval, evaluation-driven retrieval tuning, or hybrid retrieval at scale.
• Direct or transferable experience with safety, privacy, and policy constraints in user-facing AI.
• K-12 or other regulated-domain experience.
• Experience with prompt-optimization frameworks such as DSPy, TEXTGRAD, or AdalFlow where they delivered production value.
• A public repository, package, gist, technical write-up, or representative project demonstrating meaningful AI work that can be discussed within confidentiality constraints.
• Open-source contributions to AI tooling, including frameworks, agents, evaluations, or MCP servers.

Responsibilities

• Design, build, and operate production agents and agentic workflows that solve defined problems end to end.
• Own prompts, tools, retrieval, guardrails, observability, cost and latency budgets, and rollout for AI systems.
• Provide governance and security guidance related to AI design, strategy, and usage.
• Identify high-impact operational toil and partner with SMEs to define success criteria, validate outputs, and automate meaningful parts of workflows.
• Involve SMEs as co-owners of quality from the start of projects.
• Design AI features for relevant compliance frameworks, and run safety and bias evaluations before launch and continuously after launch.
• Build human-in-the-loop and content-filtering controls for AI features before they reach end users.
• Hand off production features with documentation, runbooks, an evaluation harness, and dashboards.
• Foster safe AI adoption through manageable ecosystems that enable cross-functional teams to create and enhance workflows and automations.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed