sub-AI (opt) / I. FRONTIER COGNITIVE SYSTEMS

Long-Context Intelligence Systems

Cognitive AI systems for agent behavior, reasoning, planning, context handling, simulation, and decision support. Senior AI engineer scope covers retrieval layer, embedding store, semantic index, memory policy, citation path, and data lifecycle control, using document corpus, ontology terms, access groups, query patterns, retention rules, and ground-truth answer sets and measurable checks for retrieval precision, citation accuracy, stale-memory risk, context overflow, and permission leakage.

Architecture & Risk Blueprint

Senior AI engineering discovery for architecture, risk boundaries, data readiness, and implementation scope.

For Long-Context Intelligence Systems, the AI engineer will map target workflows, data owners, integration points, and known failure modes before design starts
Define retrieval layer, embedding store, semantic index, memory policy, citation path, and data lifecycle control with clear service boundaries, control points, and engineering assumptions
Prepare the dataset, model, runtime, access, and logging requirements needed for Long-Context Intelligence Systems
Build the evaluation plan for retrieval precision, citation accuracy, stale-memory risk, context overflow, and permission leakage so acceptance is measurable, not impression-based
Document risks around unsafe action, data leakage, dependency failure, integration drift, unclear accountability, and evidence gaps and turn them into mitigation tasks with named owners
Deliver architecture diagrams, runbooks, test records, release notes, acceptance criteria, and engineering backlog for procurement, technical review, and implementation approval

USD 1.768.400 IDR 30.504.900.000 Request Scope

Controlled Prototype & Evaluation

A limited working system to test behavior, integration boundaries, evaluation criteria, and operational limits.

For Long-Context Intelligence Systems, the AI engineer will implement a controlled prototype around the highest-risk workflow, not a presentation mockup
Connect document corpus, ontology terms, access groups, query patterns, retention rules, and ground-truth answer sets to a limited runtime using test credentials, sandbox data, and strict access separation
Build the first retrieval service, reranker, memory store, prompt assembly, citation validator, and freshness monitor slice with traceable inputs, outputs, errors, and reviewer notes
Run evaluation cases for retrieval precision, citation accuracy, stale-memory risk, context overflow, and permission leakage and record pass, fail, and uncertain outcomes
Review security, data handling, prompt or policy behavior, and integration limits before production planning
Produce a prototype report with architecture changes, blocked items, engineering estimates, and release criteria

USD 2.475.652 IDR 42.705.000.000 Request Scope

Recommended

Production Engineering

Production implementation with service boundaries, pipelines, evaluation harness, security controls, and handover.

For Long-Context Intelligence Systems, the AI engineer will build the production service boundary for Long-Context Intelligence Systems with repository structure and release workflow
Implement retrieval service, reranker, memory store, prompt assembly, citation validator, and freshness monitor with environment separation, secrets handling, API contracts, and rollback path
Engineer data preparation, model routing, policy checks, test fixtures, and operational telemetry for the service
Create automated evaluation jobs for retrieval precision, citation accuracy, stale-memory risk, context overflow, and permission leakage before every accepted release
Add audit records, access controls, monitoring operational intelligence interfaces, incident notes, and dependency version tracking
Hand over diagrams, runbooks, acceptance records, deployment notes, and backlog items to the owner team

USD 3.495.948 IDR 60.305.100.000 Request Scope

Operations, Reliability & Governance

Operating model for reliability, monitoring, release control, evidence records, and long-term technical governance.

For Long-Context Intelligence Systems, the AI engineer will set up operating controls for release approval, model or policy change, incident response, and evidence storage
Define service indicators for retrieval precision, citation accuracy, stale-memory risk, context overflow, and permission leakage with alert thresholds, review cadence, and escalation roles
Create monitoring for retrieval service, reranker, memory store, prompt assembly, citation validator, and freshness monitor including latency, errors, drift, cost, version changes, and abnormal behavior
Run tabletop recovery checks for unsafe action, data leakage, dependency failure, integration drift, unclear accountability, and evidence gaps and document the decision path for urgent rollback or shutdown
Prepare governance records for access review, data retention, evaluation evidence, vendor dependency, and stakeholder reporting
Maintain an engineering roadmap for reliability, cost, security, and capability improvements after launch

USD 4.551.026 IDR 78.505.200.000 Request Scope