FieldsAI Engineer
AI Engineer
Build reliable applications on top of large language models.
Career · Capability
What you learn
- How language models work and where they fail
- Prompt design, retrieval, and tool use
- Evaluating and shipping model-backed features
- Cost, latency, and safety trade-offs in production
What you will understand
- Tokens, context windows, and embeddings
- Retrieval-augmented generation
- Evaluation and regression testing for non-deterministic systems
- Guardrails and prompt-injection defenses
How you will practice
- Write and refine prompts against a held-out test set
- Wire a retrieval pipeline over a document set
- Build an evaluation harness that scores model output
What you will build
- A question-answering assistant grounded in your own documents
- An evaluation suite that catches regressions across model versions
The proof you build
Evidence that you can design, evaluate, and ship a model-backed feature with attention to correctness, cost, and safety.
Your work is observed with your consent, scored for independence and assistance, and turned into proof that carries a confidence level. The career path can reach a high-assurance credential, anchored by a scored capstone.
Related capability paths
What is not live yet
The desktop app, consent-based observation, scoring, and credentials are in development. Nothing here implies they are live yet.
Get early access