Platform Engineer

Requirements:

• Vector Database Engines: Deep expertise in specialized vector databases (e. g., Vespa, Qdrant, Milvus) and familiarity with vector extensions in traditional DBs (e. g., pgvector).
• Distributed Systems: Strong foundation in distributed indexing, sharding strategies, and consistency models (e. g., Raft consensus, Paxos).
• Infrastructure: Kubernetes (AKS/GKE), Helm, and Terraform for large-scale, automated infrastructure provisioning and infra scaling automation, etc.
• Performance Engineering: Experience with low-latency search optimizations, quantization (product quantization, HNSW indexing, and BM25+ vector search optimization), and caching strategies.
• Monitoring and Observability: Prometheus, Grafana, Jaeger/Tempo (distributed tracing), and custom automation for health checks.
• Languages: Go/Rust (for performance-critical core platform components) and Python (for client SDKs and DS integration).
• ML Lifecycle Integration: Make vector databases available for various use cases at scale, like similarity search, vector search, RAG systems, etc.

Skills

Agentic AI, deep learning, Generative AI, Go, Kubernetes, Machine Learning, ML Platform, MLflow, platform, Python, Rust, Terraform, Vector Databases, vector search