Experience : 5 to 8 yrs email id to apply : [email protected]

Key Responsibilities • Design & architect scalable knowledge graph systems: Entity extraction, relationship inference, hierarchical graph construction, and enrichment pipelines handling billions of nodes/relationships, graph-backed RAG systems with entity linking.

- Optimize graph database performance: Neo4j query optimization, index strategies (b-tree, HNSW, full-text), traversal efficiency, bulk operations, and large-scale analytics.
- Implement distributed graph processing: High-volume ingest pipelines with idempotence, state management, consistency guarantees, and production monitoring.
- Evaluate and integrate emerging technologies: graph databases, vector stores, semantic search, LLM APIs, and AI-driven data enrichment.
- Own performance optimization across the stack: query planning, indexing strategies, caching, batch processing, and compute resource allocation.
- Collaborate with cross-functional teams (data science, backend, platform) to translate requirements into robust, production-grade systems. Technical Skills (Required)
- Graph Databases & Technologies (Core Expertise):

o Neo4j: Cypher query language, index strategies (b-tree, full-text, HNSW), query optimization and execution planning.

o Graph data modeling: entity-relationship design, schema optimization, constraint management.

o Graph algorithms: shortest path, centrality (betweenness, closeness, PageRank), community detection, k-NN similarity, link prediction.

o Graph traversal optimization: query performance tuning, index selection, caching strategies.

o Knowledge graphs: entity linking, relationship extraction, hierarchical organization, semantic enrichment. o Graph analytics at scale: aggregation, pattern matching, temporal graphs, multi-hop reasoning.

- Data Engineering:

o End-to-end pipeline design: ingestion, transformation, enrichment, indexing,



serving.

o ETL/ELT workflows, distributed query optimization, data lineage and quality.

o Experience with structured and unstructured data at scale.

- Databases & Storage:

o Relational databases (SQL optimization, query planning, schema design).

o NoSQL systems (document stores, key-value, time-series).

o Vector databases and semantic search (indexing, k-NN, HNSW, approximate nearest neighbor).

- Cloud Platforms:

o Azure services: Compute (Functions, VMs, Kubernetes), Storage (Blob, Table, CosmosDB), Azure Durable Functions, Messaging & Queues (Service Bus, Event Hub, Event Grid systems at scale), Analytics (Synapse, Data Factory, Cognitive Search).

o Serverless patterns: Functions, Logic Apps, event-driven architectures. o Infrastructure-as-Code (Bicep, Terraform, ARM templates).

o Service-to-service integration, security (Key Vault, Managed Identity, RBAC).

- Distributed Systems: o Asynchronous messaging patterns, message queues, event streaming. o State management, eventual consistency, idempotence, retry strategies. o Fault tolerance, graceful degradation, health monitoring. o Load balancing, backpressure, throttling. • Backend & Systems: o Python, Java, or equivalent production-grade language. o API design, microservices architecture. o Async/concurrent programming, dependency injection, testing. o Observability: logging, metrics, tracing (Application Insights, ELK, Prometheus). • Generative AI Systems: o LLM APIs (OpenAI, Azure OpenAI, Claude), prompt engineering,



chain-of-thought patterns. o RAG: chunking, retrieval optimization, context ranking; embedding models and vector operations. o Entity/relationship extraction, semantic understanding, LLM application architecture. o ML model serving, inference optimization, token management, cost optimization. Technical Skills (Nice to Have) • Graph Expertise: Neo4j Certifications (Associate, Skilled); PyTorch Geometric, DGL, GraphSAGE; graph embeddings (Node2Vec, GNN); RDF/semantic web; temporal/property graphs • Azure Certifications: AZ-900, AZ-104, AZ-305, DP-200, DP-900. • Advanced Graph Systems: Distributed graph processing (Spark GraphX, Gremlin), graph partitioning, scaling 100M+ nodes, multi-tenancy, sharding • System Optimization: Query execution internals, cost modeling, workload characterization, backend optimization expertise • Container & Orchestration: Docker, Kubernetes, Helm. • Open-source: Contributions to graph technology projects (Neo4j, Gremlin, etc.) Preferred Qualifications • 5–8+ years in data engineering, backend engineering, or AI/ML infrastructure roles in production environments.
- 3+ years designing and building enterprise-scale data systems, pipelines, or platform services.
- 2+ years building knowledge graphs, graph systems, or graph-backed AI/search applications (Neo4j) • 2+ years deploying generative AI systems (RAG, LLM APIs, prompt engineering) • Master's degree in Computer Science, Engineering, Mathematics, or related field; Ph.D. preferred. • Production experience with graph databases at scale (millions to billions of nodes) • Hands-on cloud experience (Azure, AWS, or GCP) • Expertise in vector databases or semantic search at scale. • Background in backend systems optimization (database engines, query optimization, indexing strategies).

📌 Graph Tech Expert (Noida)
🏢 PharynxAI
📍 Noida