AI Engineer
netapp
Job Description
- Design and implement REST/gRPC APIs in Python (FastAPI, Flask, or similar) for AI/ML features and internal services Integrate LLMs, embeddings, RAG pipelines and agents into production workflows
- Build reliable data ingestion, preprocessing, and inference pipelines with clear observability
- Profile and optimize latency, throughput, memory usage, and cost (batching, caching, async I/O, connection pooling)
- Implement logging, metrics, tracing, and alerting for AI services (Dynatrace, Grafana, OpenTelemetry, etc.)
- Write unit, integration, and load tests; participate in code reviews and production incident response
- Collaborate with ML engineers on model serving, versioning, A/B testing, and safe rollout
- Document APIs, runbooks, and architecture decisions for maintainability
- 5–8 years of professional software development experience
- Strong Python skills and experience building production APIs
- Hands-on experience with API frameworks (e.g. FastAPI, Flask, Django REST)
- Proven ability to debug scalability and reliability issues in distributed systems
- Experience with SQL/NoSQL databases, caching (Redis), and message queues (Kafka, RabbitMQ, SQS, etc.)
- Solid understanding of async programming, concurrency, and I/O-bound vs CPU-bound bottlenecks
- Experience deploying services in Docker/Kubernetes or similar container platforms
- Familiarity with CI/CD, Git, and agile delivery