Ai Engineer Jobs

About The Position

Requirements

• Experience building and shipping Python services or product features in production.
• Ability to reason about testing, observability, reliability, security, cost, and latency.
• Understanding of common LLM failure modes and how context, data quality, evaluation design, and model or API choices affect results.
• Hands-on experience with structured outputs, tool calling, context design, or retrieval.
• Ability to use source artifacts, traces, ground truth, evaluation sets, structured error analysis, tests, and production evidence to diagnose failures and determine whether changes helped.
• Ability to shape underspecified work with domain experts, learn field meanings and rules, make progress, and identify decisions requiring broader input.
• Practical judgment in choosing among deterministic code, schemas, rules, search, product changes, and LLMs.
• Ability to delegate implementation to coding agents with suitable context and verification, set an appropriate level of autonomy, and review, test, and correct their work.
• Authorization to work for any employer in the United States; Fortegra cannot sponsor or assume sponsorship of employment visas now or in the future.

Nice To Haves

• Experience with document processing, OCR, information extraction, retrieval, or search.
• Experience in insurance or another regulated, document-intensive domain.
• Experience with Azure, serverless systems, or distributed processing.
• Experience with evidence, provenance, citation, or human-review systems.
• Experience with Claude Code, OpenAI Codex, Cursor, or similar coding-agent tools; experience with Fortegra's exact tools is optional.

Responsibilities

• Build applied-AI product features across document parsing and OCR, classification and routing, structured extraction, normalization and reconciliation, source grounding, retrieval and summarization, and deterministic logic.
• Inspect real documents, traces, and model behavior; maintain representative evaluation sets; classify failures; choose changes based on evidence; and requalify results.
• Ensure outputs are complete, support material claims with source evidence, and reconcile related values.
• Work with underwriters, auditors, claims professionals, and other specialists to clarify definitions, exceptions, source authority, and acceptance criteria.
• Translate domain decisions into schemas, examples, validation rules, and product behavior.
• Compare models, OCR and parsing tools, managed services, and internal implementations on representative documents; recommend approaches based on quality, cost, latency, reproducibility, failure modes, and operational overhead.
• Build production features, debug system behavior, review code, improve tests and observability, and operate services in a Python and Azure Functions codebase.
• Take bounded features from business questions or production failures through planning, implementation, evaluation, and production readiness.
• Improve an existing capability through evaluation and requalification, ship a bounded document-intelligence feature, and complete a technical comparison with tests, artifacts, and handoff.
• Use deterministic code for stable rules and LLMs for variable interpretation, supporting release decisions with tests, evaluations, and production evidence.
• Work effectively with coding agents by providing context and verification, setting appropriate autonomy, and retaining responsibility for architecture, review, testing, and merged work.
• Investigate failures across documents, prompts, model behavior, application logic, and product expectations, and preserve concise plans, findings, and handoffs.

Benefits

• Full benefit package including medical, dental, life, and vision coverage, company-paid short- and long-term disability, 401(k), tuition assistance, and more.