AI Platform Engineer

Programmers Planet; Lahore; On-site; PKR 3,000,000 - 5,400,000; Full time

Job summary

Programmers Planet in Lahore, Pakistan, is seeking an experienced backend/full-stack developer to own an AI-powered knowledge platform. You will lead ingestion pipelines, multi-source RAG workflows, and the full-stack app on top.

You will build Python backends (FastAPI) and JavaScript frontends, implement authentication and secure data access, and drive CI/CD with Azure DevOps in a data-rich, security-first environment.

Qualifications

• 5+ years of strong Python and backend development experience.
• Hands-on experience building LLM applications and RAG pipelines.
• Data ingestion, REST APIs, webhooks, and third-party integrations.
• Full-stack skills with JavaScript/Node.js.
• Azure DevOps, Git workflows, and CI/CD.
• Solid grasp of authentication, authorization, and secure data access.

Responsibilities

• Build a unified ingestion pipeline using APIs, webhooks, and connectors.
• Design multi-source RAG workflows: chunking, embeddings, indexing, retrieval.
• Enable AI understanding of large codebases and auto-generate architecture docs.
• Develop Python (FastAPI) backends and JavaScript frontends for search, intake, visualization.
• Enforce permission-aware retrieval, provenance, and auditability across the pipeline.
• Apply TDD, automated testing, and CI/CD via Azure DevOps.

Skills

Python backend

LLM / RAG

REST APIs

Webhooks

JavaScript / Node.js

Azure DevOps

Git workflows

Authentication & Authorization

Tools

FastAPI

Pydantic

LangChain

LlamaIndex

Job description

About the Role

We’re building an AI-powered knowledge platform that pulls together data from code repositories, documentation, and project tools (Git, Jira, Azure DevOps, Quickbase, Office docs, meeting transcripts) so AI can deliver accurate, source-grounded answers for requirements, codebase analysis, and AI-assisted development. You’ll own the platform end to end: ingestion pipeline, multi-source RAG, and the full-stack app on top.

What You’ll Do

• Build a unified, incremental ingestion pipeline using APIs, webhooks, and connectors, with parsing, normalization, deduplication, and metadata extraction
• Design multi-source RAG workflows: chunking, embeddings, indexing, hybrid retrieval, reranking, and context assembly
• Enable AI understanding of large codebases (structure, symbols, dependencies, APIs) and auto-generate architecture documentation
• Develop Python (FastAPI) backend services and JavaScript/Node.js frontends for search, intake, and visualization
• Enforce permission-aware retrieval, provenance, and auditability across the pipeline
• Apply TDD, automated testing (including retrieval-quality tests), and CI/CD via Azure DevOps

Must Have

• 5+ years of strong Python and backend development experience
• Hands-on experience building LLM applications and RAG pipelines
• Data ingestion, REST APIs, webhooks, and third-party integrations
• Full-stack skills with JavaScript/Node.js
• Azure DevOps, Git workflows, and CI/CD
• Solid grasp of authentication, authorization, and secure data access

Nice to Have

• FastAPI, Pydantic, LangChain or LlamaIndex
• Vector databases (Pinecone, ChromaDB, FAISS) and retrieval evaluation
• AST parsing, symbol indexing, dependency graphs, knowledge graphs
• Docker, cloud infrastructure, observability
• Jira and Quickbase integrations, plus AI governance controls

Why Join

Build a high-impact AI platform from the ground up, working closely with architects and product stakeholders in an iterative, security-first team.