Generative AI Engineer

Job description:

KEY RESPONSIBILITIES

Design and own multi-stage ingestion pipelines handling HTML, PDF, and image sources with layout parsing, metadata extraction, and vector storage

Architect RAG systems with hybrid search (BM25 + semantic), document versioning, and cross-reference resolution

Build production-grade FastAPI services with typed response envelopes, OpenAPI compliance, and Langfuse tracing integration

Engineer prompt systems structured prompts, prompt versioning, few-shot strategies, and judge-based evaluation

Integrate and manage LLM routing via LiteLLM: model fallback, cost control, and per-route configuration

Design agentic workflows using LangGraph: multi-step retrieval, tool use, and conditional branching

Build and maintain knowledge graphs in NebulaGraph / Neo4j entity extraction, relationship modelling, and domain ontology alignment

Implement graph-augmented retrieval (GraphRAG) combining vector search with graph traversal to surface contextually connected information beyond chunk-level retrieval

Own entity linking and co-reference resolution pipelines that connect ingested documents to graph nodes

Lead RAG evaluation initiatives define metrics, build eval datasets, and run regression cycles

Drive observability standards tracing, cost attribution, and latency profiling via Langfuse

Collaborate on K8s deployment patterns for AI services: resource limits, GPU scheduling, and health probes

Mentor junior developers and conduct code and prompt reviews

REQUIRED SKILLS

Python (5+ years) async, concurrency patterns, production packaging

Deep understanding of RAG hybrid retrieval, reranking, chunking strategies, embedding model selection

FastAPI dependency injection, middleware, background tasks, async patterns

Prompt engineering structured prompting, chain-of-thought, evaluation-driven iteration

LLM API integration OpenAI-compatible APIs, AWS Bedrock, or similar

Vector DB expertise Weaviate or equivalent: schema design, indexing, and filtering

Document parsing at scale Docling, layout models, VLM-based extraction from PDFs, HTML, and images

Graph DB NebulaGraph or Neo4j: schema design, Cypher / nGQL queries, knowledge graph construction

Observability mindset tracing, evaluation loops, cost-aware system design