About the Role :

We're looking for a Senior AI Engineer to help build and scale dunnhumby's Enterprise AI Platform - designing, deploying, and operating production grade AI systems used across engineering teams. You'll work across the full AI lifecycle : model training and fine-tuning, agentic workflows, RAG, AI observability, and AI-powered user experiences, using the latest advancements in Generative AI.

What You'll Do :

- Build reusable, scalable AI services for prompt orchestration, model routing, embeddings, structured generation, and tool calling; develop configurable multi-provider AI runtimes and secure cloud-native microservices.

- Design multi-agent and autonomous systems with reasoning, planning, memory, and tool execution; build graph-based, long-running workflows with human-in-the-loop checkpoints using MCP and A2A.

- Build enterprise-grade RAG pipelines - ingestion, chunking, embeddings, hybrid search, reranking, citations - and continuously evaluate retrieval quality.

- Train, fine tune (LoRA/QLoRA/PEFT), and evaluate ML/DL models; build training pipelines, run experimentation and hyperparameter optimization, and productionize models with data science partners.

- Deploy, monitor, and continuously improve agents and models in production - experiment tracking, model registry, versioning/rollback, drift and cost monitoring, CI/CD, and canary/blue-green deployments.

- Implement guardrails for hallucination, prompt injection, and PII; establish evaluation, monitoring, and responsible-AI compliance practices.

- Build and deploy cloud-native AI services (Docker, Kubernetes, Terraform) on GCP and Azure with autoscaling, observability, and distributed tracing; own services from build through production support.

- Build responsive React-based interfaces for chat, copilots, prompt playgrounds, and agent/evaluation dashboards, integrated via REST, SSE, and WebSockets.

- Write clean, tested code; drive architecture reviews, code reviews, and mentor engineers.

What You'll Bring :

- Bachelor's/Master's in Computer Science, AI, Engineering, or related field.

- 8+ years of software engineering experience, including 3+ years building production AI/ML applications.

- Strong grounding in distributed systems, cloud-native architecture, and microservices.

- Track record delivering enterprise-grade AI solutions from POC to production.

Technical Skills :

- Programming : Python (expert), TypeScript/JavaScript, SQL, async programming, REST & gRPC, design patterns

- AI/ML Concepts : LLMs, prompt engineering, embeddings, RAG, hybrid search, agentic AI (tool/function calling, MCP, A2A), model training & fine-tuning (LoRA/QLoRA/PEFT), hyperparameter optimization, GPU optimization, quantization

- AI Frameworks : LangChain, LangGraph, Google ADK, OpenAI Agents SDK, CrewAI, AutoGen, LlamaIndex, Semantic Kernel, DSPy, Pydantic AI

- Cloud AI Platforms : Google Vertex AI, Azure AI Foundry, Azure OpenAI, Model Garden

- ML & MLOps : PyTorch, TensorFlow, Hugging Face, MLflow, Kubeflow, model registry, experiment tracking, continuous training

- AgentOps & Observability : LangSmith/Langfuse/Arize Phoenix, OpenTelemetry, Grafana, New Relic, agent evaluation, cost monitoring

- Vector Databases : Pinecone/Weaviate/Milvus/pgvector/Vertex AI Vector Search/Azure AI Search

- Cloud & DevOps : Docker, Kubernetes, Terraform, ArgoCD, GitHub Actions/Azure DevOps, CI/CD, IaC

- Workflow Orchestration : Temporal/Argo Workflows/event-driven architecture/message queues