Senior Data Science Engineer
On-siteBengaluru, Karnataka, India
Job Summary
Design and implement production-grade GenAI and agentic AI pipelines on Google Cloud Platform using Vertex AI, ADK frameworks, and Apache Beam. Build RAG systems, agent planners, and tool integrations while ensuring operational readiness through observability, logging, and cost optimization. Collaborate with engineering leads to align architecture standards, conduct code reviews, and mentor junior engineers on prompt engineering and GCP best practices. Apply responsible AI principles including safety prompts, content filters, and audit logging to maintain security and compliance. Deliver features with minimal defects while meeting evaluation metrics for faithfulness and grounding.
Required Qualifications
- 5–8 years in software/data/ML engineering
- 1–2 years in GenAI/agentic systems
- Hands-on experience with GCP AI stack and ADK-based agent development
- Strong coding skills in Python/TypeScript
- Familiarity with infrastructure-as-code
- Hands-on experience on Java
- Experience with Dataflow + Beam
- Experience with Spark
- Exposure to LLMOps practices
- Experience with production deployments
- GenAI: Prompt engineering
- GenAI: RAG
- GenAI: embeddings
- GenAI: fine-tuning
- GenAI: evaluation metrics
- Agentic AI (ADK): Agent loops
- Agentic AI (ADK): tool integration
- Agentic AI (ADK): memory handling
- Agentic AI (ADK): planning strategies
- GCP Services: Vertex AI
- GCP Services: BigQuery
- GCP Services: Cloud Storage
- GCP Services: Pub/Sub
- GCP Services: Cloud Run
- GCP Services: Workflows
- LLMOps: CI/CD pipelines
- LLMOps: model registry
- LLMOps: telemetry
- LLMOps: cost/performance dashboards
- Security & Compliance: IAM
- Security & Compliance: VPC-SC
- Security & Compliance: DLP
- Security & Compliance: Okta/IAP integration
- Data pipeline: Dataflow
- Data pipeline: Apache Beam
- Data pipeline: Java
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.