Tech Stack
AWSAzureCloudGoogle Cloud PlatformMicroservicesPythonTerraform
About the role
- Partnering with stakeholders to scope problems and identify the right solution
- Designing and implementing agentic systems using RAG, grounding, prompt engineering, and orchestration on a GCP-first stack
- Building and maintaining production ML pipelines and services for non-GenAI use cases (recommender systems, customer segmentation, marketing optimisation)
- Developing APIs and microservices for AI/ML solutions, ensuring security, scalability, and observability
- Implementing CI/CD for ML services, writing infrastructure as code, and monitoring for model/data drift and performance
- Establishing robust guardrails for safe AI usage, including prompt security, practical evaluation frameworks, and privacy compliance
- Driving and evangelizing best practices, reusable templates, and documentation to scale AI/ML delivery
- Collaborating with data engineers, data scientists, front & back-end engineers, product managers, legal & infosec colleagues to deliver end-to-end solutions
Requirements
- Bachelor’s or Master’s degree in Computer Science, Engineering, or related field
- Strong Python engineering skills (FastAPI, testing, typing)
- Experience with cloud-native development (GCP preferred)
- Hands-on experience with GCP Vertex AI or equivalent cloud-native ML platforms (AWS SageMaker, Azure ML)
- Experience with agent orchestration frameworks such as LangChain and LangGraph
- Solid understanding of MLOps: CI/CD, IaC (Terraform), experiment tracking, model registry, and monitoring
- Proven experience deploying and operating ML systems in production (batch and real-time)
- Familiarity with RAG architectures, prompt engineering, and evaluation techniques
- Strong grasp of security, privacy, and governance principles (IAM, secrets, PII handling)
- Excellent communication skills and ability to work with non-technical stakeholders
- (Nice to have) Experience with vector databases and retrieval strategies
- (Nice to have) Knowledge of recommender systems and ranking models
- (Nice to have) Familiarity with LLM evaluation tools (e.g., RAGAS, TruLens, LangSmith, Arize)
- (Nice to have) Exposure to feature stores, data lineage, and observability stacks
- (Nice to have) Experience in e-commerce or retail environments
- (Nice to have) Demonstrable ability to weigh up build/build/configure decisions in the LLM space