Senior AI Engineer - Agent Orchestration & Graph RAG
New
H
HR WaysAI applications
United States, 9:00 AM–5:00 PM Eastern Standard Time (EST)Full-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 6+ years of professional software engineering experience
- Required Skills
- PythonSQL
Requirements
- Have 6+ years of professional software engineering experience with substantial ownership of production backend or distributed systems.
- Have experience shipping and operating LLM applications, agent workflows, or RAG systems used by real customers.
- Demonstrate strong Python skills, including asynchronous programming, API development, testing, profiling, and debugging.
- Have experience with LangGraph, LangSmith, or comparable orchestration systems.
- Have practical knowledge of embeddings, vector search, hybrid retrieval, reranking, and structured model outputs.
- Demonstrate strong SQL skills and experience optimizing database queries.
- Have experience building ingestion or ETL/ELT pipelines with validation, retries, incremental processing, and recovery.
- Demonstrate improvements to production quality, latency, reliability, or cost.
- Communicate clearly and own technical problems from investigation through production delivery.
- Preferred: Neo4j, Cypher, knowledge modeling, Graph RAG, or graph databases.
- Preferred: Experience with consumer-facing AI applications.
- Preferred: Qdrant, PostgreSQL, Supabase, TypeScript, or Next.js.
Responsibilities
- Build and improve agent workflows for claim analysis, retrieval, verification, and response generation.
- Optimize orchestration, including routing, state management, parallel execution, retries, and failure recovery.
- Design and optimize graph, SQL, and vector-search queries, indexing strategies, filtering, and reranking.
- Build knowledge-ingestion pipelines for validation, entity resolution, deduplication, incremental updates, and re-indexing.
- Preserve source provenance and citation metadata while keeping graph and vector representations consistent.
- Reduce response times and costs through profiling, caching, concurrency management, model selection, and context management.
- Build evaluations and regression checks 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.
View Full Description & ApplyYou'll be redirected to the employer's site
