Senior AI Engineer – Agent Orchestration, Graph RAG

This is a fully remote position, open to applicants in Pakistan.

📋 Description

• Develop and enhance workflows for agents related to claim analysis, retrieval, verification, and response formulation.

• Streamline orchestration processes, encompassing routing, state management, parallel execution, retries, and recovery from failures.

• Design and refine graph, SQL, and vector-search queries, along with indexing strategies, filtering mechanisms, and reranking techniques.

• Create dependable knowledge-ingestion pipelines that address validation, entity resolution, deduplication, incremental updates, and re-indexing.

• Maintain the provenance of sources and citation metadata while ensuring consistency in graph and vector representations.

• Enhance response times and reduce costs through profiling, caching, managing concurrency, selecting models, and administering efficient context management.

• Establish evaluations and regression tests to assess retrieval quality, verdict accuracy, citation correctness, and effective handling of insufficient evidence.

• Oversee production systems, examine failures, and collaborate with product engineers and domain experts.

⛳️ Requirements

• A minimum of 6 years of professional experience in software engineering, with significant responsibility for production backend or distributed systems.

• Proven experience in deploying and maintaining LLM applications, agent workflows, or RAG systems used by actual customers.

• Proficient in Python, including asynchronous programming, API development, testing, profiling, and debugging.

• Familiarity with LangGraph, LangSmith, or similar orchestration systems.

• Practical understanding of embeddings, vector search, hybrid retrieval, reranking, and structured model outputs.

• Strong SQL capabilities and experience in optimizing database queries.

• Background in building ingestion or ETL/ELT pipelines that include validation, retries, incremental processing, and recovery.

• Demonstrated contributions to improvements in production quality, latency, reliability, or cost efficiency.

• Excellent communication skills and the ability to manage technical challenges from investigation to production delivery.

• Preferred: Experience with Neo4j, Cypher, knowledge modeling, or Graph RAG / Graph databases.

• Preferred: Involvement in consumer-facing AI applications.

• Preferred: Familiarity with Qdrant, PostgreSQL, Supabase, TypeScript, or Next.js.

• Preferred: Experience in multilingual or Arabic retrieval and evaluation.

• Preferred: Skills in text, image, audio, or video processing.

🏝️ Benefits

• 21 paid working days per year, inclusive of vacation, personal, and sick leave.

• Recognized holidays, including major Islamic holidays.