2 months ago
Remote, WorldwideSenior
Responsibilities
- Own the technical customer relationship as the primary professional services contact across discovery, design, pilot, production, and expansion.
- Run customer discovery, identify high-value use cases, define success criteria, and create phased delivery plans.
- Design ArangoDB multi-model architectures, graph data models, AQL query and traversal patterns, and GraphRAG retrieval solutions.
- Build reference implementations and prototypes including graph schemas, data connectors, GraphRAG pipelines, agent orchestration, and APIs.
- Guide secure, observable production deployments with testing, CI/CD, and infrastructure-as-code.
- Architect graph, vector, and hybrid retrieval using chunking, embeddings, ranking, caching, and tool or agent orchestration.
- Establish evaluation practices using offline and online metrics, prompts, models, retrieval strategies, graph structures, and A/B tests.
- Design ETL/ELT pipelines, vector indices, graph ingestion, and metadata governance.
- Define monitoring and alerting for quality, drift, hallucinations, guardrail events, latency, and cost.
- Architect role-based access, secrets management, audit logging, PII redaction, and content safety controls.
- Meet applicable SOC 2, ISO 27001, GDPR, CCPA, and HIPAA requirements.
- Produce architecture documentation and runbooks, train customer engineers and end users, and enable customer self-sufficiency.
- Represent customer feedback to Arango’s product and engineering teams and help shape the roadmap.
Requirements
- Deep expertise in graph data modeling, graph queries and traversal, graph algorithms, and knowledge-graph design for AI.
- Hands-on experience building GraphRAG or knowledge-graph-backed retrieval for LLM applications.
- At least 5 years of experience in software engineering, solution architecture, or technical professional services, including building and operating production systems.
- Strong applied AI and Python skills with knowledge of data structures, systems design, concurrency, and networking.
- Strong database skills across graph, NoSQL, key-value, and document models; multi-model experience is valued.
- Hands-on experience with modern LLMs, Hugging Face, LangChain or LlamaIndex, and function or tool calling.
- Experience with retrieval and vector databases such as FAISS, pgvector, Pinecone, or Weaviate and with hybrid graph-vector retrieval.
- Experience with AWS, GCP, or Azure; Docker, Kubernetes, infrastructure-as-code, and CI/CD.
- Experience with observability, performance tuning, and latency-sensitive services.
- Excellent customer-facing communication skills, including executive- and engineering-level technical discussions.
- Preferred: Direct ArangoDB or production graph database deployment experience.
- Preferred: Search and information-retrieval fundamentals including BM25, hybrid retrieval, re-ranking, ColBERT, or cross-encoders.
- Preferred: TypeScript, React, and Next.js experience for light UI prototyping.
- Preferred: MLOps and evaluation experience with MLflow, Weights & Biases, Ragas, promptfoo, or DeepEval.
- Preferred: Awareness of LoRA/PEFT, DPO, distillation, quantization, vLLM, TGI, or TensorRT-LLM.
- Preferred: Domain experience in finance, healthcare, public sector, manufacturing, or retail.
- Preferred: Security and compliance familiarity including data residency, KMS/HSM, and private networking.
- French government or industry experience is a plus.
Benefits
- Remote position.
- Opportunity to work on AI and data infrastructure, collaborate with experienced cross-functional teams, and shape enterprise AI application architecture and the product roadmap.
Tech Stack
Apache AirflowApache KafkaAWSAzureDockerFastAPIGitHub ActionsGoogle BigQueryGoogle Cloud PlatformGrafanagRPCKubernetesMLflowNext.jsPostgreSQLPrometheusPythonReactSnowflakeTerraformTypeScript
Categories
Solutions Engineering