$2,434.00 Fixed
TechFlow Inc
Contract · Remote · Flexible hours
About the role
TechFlow Inc is revamping its legacy production platform, codenamed "PulseForge," to achieve zero‑downtime deployments. As an AI Machine Learning Engineer you will design and integrate intelligent components that enable seamless feature roll‑outs while preserving existing workloads. The project focuses on modernizing data pipelines and model serving layers without interrupting live traffic.
Key responsibilities
- Architect a real‑time inference microservice using FastAPI and TensorFlow Serving for PulseForge.
- Implement a canary‑release framework with Kubernetes and Istio to validate model updates without downtime.
- Refactor legacy batch scoring jobs into streaming pipelines on Apache Flink, ensuring sub‑second latency.
- Develop automated CI/CD pipelines in GitLab CI that include model versioning and automated rollback.
- Collaborate with data engineers to migrate feature stores to Feast, maintaining data consistency during migration.
- Monitor model drift and performance using Prometheus alerts and Grafana dashboards.
Must-have skills
- Advanced Python programming for ML model development and deployment.
- Experience with Kubernetes, Docker, and container orchestration.
- Proficiency in building RESTful APIs for model serving.
- Strong background in MLOps tools such as MLflow, GitLab CI, and Terraform.
- Knowledge of zero‑downtime deployment patterns and canary testing.
Nice to have
- Familiarity with Apache Flink or Spark Structured Streaming.
- Experience with monitoring stacks like Prometheus/Grafana.
- Proposal: 0
- Less than 3 month
Chris Boling
,
Member since
Oct 27, 2025
Total Job