AI Engineer - Agentic Systems & LLMs

Reveal Technology

19h•$150,000 - $200,000

About The Position

Reveal is building an AI-native system that replaces manual staff work with intelligent, explainable automation. The end state is not âAI assistance,â but earned delegation, software that progressively assumes responsibility as users demonstrate competence and trust. This role exists to design and build the agentic intelligence layer that makes that progression possible. You will create AI systems that start as advisors, mature into copilots, and ultimately become trusted operators, all while remaining transparent, bounded, auditable, and aligned to doctrine and policy.

Requirements

Strong hands-on experience with developing and deploying LLM-based systems in production
Experience building multi-step agentic AI systems
Experience in MLOps, automating the process of training and deploying models and supportive architecture
Must have experience with containerization approaches such as Docker and Kubernetes
Developed CI/CD pipelines for testing and automation
Experience in developing or utilizing third party solutions to evaluate and quantify model performance
Proficiency in Python
Experience with: LLM orchestration, RAG architectures, Function/tool calling, State management across AI workflows, Vector Databases
Ability to reason about constraints, optimization, and dependencies
Comfort operating in ambiguous, fast-moving product environments

Nice To Haves

Experience with planning, scheduling, or optimization systems
Experience with policy-driven or regulated environments
Familiarity with trust modeling, human-in-the-loop systems, or safety rails
Prior work on systems where AI actions had real-world consequences
Willingness to engage deeply with users and iterate based on behavior, not theory

Responsibilities

Design and implement production-grade LLM and agentic systems that ingest operational, doctrinal, and policy data and transform it into structured tasks, workflows, and resource-aware plans.
Build orchestration layers across workflows, tools, and human approvals to support a recommendation-first AI copilot with progressive, user-authorized agentic actions.
Implement RAG pipelines over doctrine, regulations, and historical data to enable constraint-aware reasoning, sequencing logic, and transparent, explainable recommendations.
Design trust, permissioning, and rollback mechanisms that adapt system autonomy based on user behavior, experience, and operational risk.
Instrument systems for auditability, traceability, and user trust, ensuring all outputs can be explained and linked back to source inputs.
Optimize AI systems for latency, cost, reliability, and explainability in real-world operational environments.
Collaborate closely with product, UX, engineering, and domain experts to translate complex operational workflows into scalable, human-centered AI systems.