Senior AI Engineer – LangGraph & Graph RAG

About the role

We are seeking a senior AI engineer to enhance our consumer application that verifies Islamic claims against traceable sources. The role focuses on building robust pipelines that turn source material into reliable answers, covering knowledge ingestion, retrieval, agent orchestration, and production performance.

Key responsibilities

• Design and improve agent workflows for claim analysis, retrieval, verification, and response generation.
• Optimize orchestration components such as routing, state management, parallel execution, retries, and failure recovery.
• Develop and fine‑tune graph, SQL, and vector‑search queries, indexing strategies, filtering, and reranking.
• Build reliable knowledge‑ingestion pipelines with validation, entity resolution, deduplication, incremental updates, and re‑indexing while preserving provenance and citation metadata.
• Reduce response latency and cost through profiling, caching, concurrency management, model selection, and efficient context handling.
• Implement evaluation and regression tests for retrieval quality, verdict accuracy, citation correctness, and handling of insufficient evidence.
• Monitor production systems, investigate failures, and collaborate with product engineers and domain specialists.

Required profile

• 6+ years of professional software engineering experience with ownership of production backend or distributed systems.
• Proven experience shipping LLM applications, agent workflows, or RAG systems used by real customers.
• Strong Python expertise, including asynchronous programming, API development, testing, profiling, and debugging.
• Experience with LangGraph, LangSmith or comparable orchestration frameworks.
• Practical knowledge of embeddings, vector search, hybrid retrieval, reranking, and structured model outputs.
• Solid SQL skills and ability to optimise database queries.
• Experience building ingestion or ETL pipelines with validation, retries, incremental processing, and recovery.

Required skills

• Python
• FastAPI
• LangGraph / LangSmith
• SQL
• Neo4j, Cypher
• Qdrant
• PostgreSQL
• Supabase
• TypeScript, Next.js

What we offer

• 21 paid working days annually covering vacation, personal, and sick leave, plus major Islamic holidays.
• Remote work from Karachi with a standard Monday‑Friday schedule (9:00 AM–5:00 PM EST).