← Back to Skills
AI & Machine LearningTechnologyPlatinum

Deploying AI models using TensorFlow on Google Cloud.

TensorFlow/Keras Engineer

TensorFlow, Keras, Google Cloud

expertv5.0

Best for

  • Building TensorFlow Serving REST/gRPC endpoints for production model inference
  • Optimizing tf.data pipelines with caching, prefetching, and parallel processing
  • Implementing distributed training strategies across multi-GPU and multi-node setups
  • Converting models to TF Lite for mobile/edge deployment with quantization

What you'll get

  • Complete tf.data pipeline code with interleave, cache, and prefetch optimizations including performance benchmarks
  • Multi-GPU distributed training implementation using MirroredStrategy with proper data sharding and gradient aggregation
  • TensorFlow Serving deployment configuration with batching, model versioning, and monitoring setup
Expects

Clear problem definition with model architecture requirements, data characteristics, and deployment constraints (latency, throughput, edge vs cloud).

Returns

Production-ready TensorFlow code with optimized data pipelines, model architectures, training loops, and deployment configurations including performance benchmarks.

What's inside

You are a TensorFlow/Keras Engineer. You build production-grade ML models using TensorFlow's ecosystem, optimizing for performance, scalability, and deployment across cloud, edge, and mobile environments. - Architect end-to-end ML systems spanning data pipelines (tf.data), model training (distribute...

Covers

What You Do DifferentlyMethodologyWatch For
Not designed for ↓
  • ×PyTorch model development or conversion to ONNX format
  • ×MLOps platform architecture beyond TensorFlow ecosystem tools
  • ×Cloud infrastructure provisioning or Kubernetes cluster management
  • ×Data preprocessing workflows outside of tf.data and TFX Transform

SupaScore

88.85
Research Quality (15%)
8.85
Prompt Engineering (25%)
9.25
Practical Utility (15%)
8.65
Completeness (10%)
8.75
User Satisfaction (20%)
8.95
Decision Usefulness (15%)
8.55

Evidence Policy

Standard: no explicit evidence policy.

tensorflowkerastf-servingtf-litetfxdeep-learninggoogle-cloud

Research Foundation: 6 sources (4 official docs, 2 paper)

This skill was developed through independent research and synthesis. SupaSkills is not affiliated with or endorsed by any cited author or organisation.

Version History

v5.03/25/2026

v5.5 final distill

v2.02/26/2026

Pipeline v4: rebuilt with 3 helper skills

v1.0.02/15/2026

Initial version

Works well with

Need more depth?

Specialist skills that go deeper in areas this skill touches.

Common Workflows

TensorFlow Production ML Pipeline

End-to-end workflow from model development through production serving with observability

© 2026 Kill The Dragon GmbH. This skill and its system prompt are protected by copyright. Unauthorised redistribution is prohibited. Terms of Service · Legal Notice