ARAL Development Lead (Python, Rules Engine, LLM/RAG) - TechMantra Global at TechMantra Global | Torre

ARAL Development Lead (Python, Rules Engine, LLM/RAG) - TechMantra Global

Emma highlights
This highlight was written by Emma’s AI. Ask Emma to edit it.
Full-time

Legal agreement: Employment

Provide your expected compensation while applying
location_on
Remote (anywhere)
Shared by
R
5 days ago

Responsibilities


Mandatory SkillsExpert Python EngineeringRules Engine DevelopmentSchema ValidationExcel / Word Parsing & Extraction PipelinesLLM Application ArchitectureStructured Outputs & Confidence ThresholdsRAG ArchitectureSelf-Hosted / Open-Weight LLM DeploymentData Sovereignty / In-Perimeter ProcessingTest-Driven DevelopmentAccuracy Validation MethodologyVersioned Configuration ManagementTeam Leadership & Sprint DeliveryKey ResponsibilitiesOwn the end-to-end architecture of the ARAL (AI Review Acceleration Layer) MVPDesign ingestion → parsing/extraction → deterministic checks → LLM checks → Pre-Check Report → audit logImplement the “Deterministic First, LLM Second” architectureOwn and maintain the versioned Pre-Check Report JSON schemaLead sprint planning, sequencing, estimation, and deliveryDrive deterministic checks for DA2, DA3 and DA4Lead LLM checks, RAG implementation, and accuracy validationManage standards artefacts as version-controlled operational configurationOwn status aggregation and SLA attainment logicEnsure data sovereignty through in-perimeter processing with no external egressLead the Track B team and coordinate with programme leadership and other teamsPreferred / Added AdvantagevLLM / Self-Hosted Open-Weight Model Production ExperienceGovernment Audit & Traceability ExperienceData Quality / Metadata Tooling Experience