Full Stack Developer With AI Integration

Role Overview

Build and deploy production AI systems within client environments, turning business needs into working applications, agents, retrieval-augmented generation (RAG) systems, and machine-learning workflows. The role combines software engineering, architecture, and client collaboration, with a focus on Google Cloud and integrations with other cloud and data platforms.

Responsibilities

• Work with client teams to understand their workflows, data, and technical constraints, then shape AI solutions around measurable needs.
• Design, build, and deploy LLM-powered applications, multi-agent systems, RAG solutions, and ML pipelines using Vertex AI and Gemini.
• Develop scalable ETL/ELT pipelines across BigQuery, Cloud Storage, Snowflake, Databricks, Amazon S3, Azure Data Lake, and operational systems.
• Connect AI solutions with Google Workspace, Apigee, Cloud Run, Pub/Sub, Cloud Functions, and identity services.
• Design secure multi-cloud architectures, including cross-cloud identity, networking, and data movement.
• Improve production reliability through evaluation benchmarks, observability and tracing, cost controls, guardrails, and automated CI/CD.
• Share reusable patterns, components, and product feedback with internal engineering and solutions teams.
• Explain technical trade-offs, demonstrate progress, and present results to technical and executive audiences.

Required Skills

• At least five years of software engineering experience, including two or more years building and deploying production ML or LLM systems.
• Strong Python skills, working knowledge of SQL, and experience with at least one of TypeScript, Go, or Java.
• Hands-on Google Cloud experience with Vertex AI and Gemini, BigQuery, Cloud Run or GKE, Cloud Storage, Pub/Sub, IAM, and VPC networking.
• Ability to provision and configure GCP infrastructure using infrastructure as code, including service accounts and networking.
• Production LLM engineering experience, including prompt design and optimization, advanced RAG, hybrid or vector retrieval, reranking, tool and API calling, agents, evaluation, and guardrails.
• Data engineering experience building resilient ETL/ELT pipelines, modeling schemas, managing vector databases, and working with complex unstructured enterprise data.
• Understanding of batch and streaming ingestion, execution performance, data partitioning, and cost optimization.
• Working knowledge of infrastructure as code, CI/CD, and containers, such as Terraform, GitHub Actions or Cloud Build, and Docker or Kubernetes.
• Ability to work through ambiguous requirements and independently drive solutions from problem definition to deployment.

Nice to Have

• Experience with AWS services such as Bedrock, SageMaker, S3, and Lambda, or with cross-cloud networking and IAM.
• Experience with Azure OpenAI, Azure ML, Data Lake Storage, or Entra ID.
• Snowflake experience, including Cortex, Snowpark, secure data sharing, or data movement between Snowflake and BigQuery.
• Databricks experience with Mosaic AI, MLflow, Unity Catalog, Delta Lake, or Spark.
• Google Cloud certifications in machine learning, agentic architecture, cloud architecture, or data engineering.
• Experience with Google ADK, LangGraph, LlamaIndex, or MCP.
• Background in consulting, solutions engineering, or a startup environment.
• Experience in regulated industries such as healthcare, financial services, or the public sector, including related compliance requirements such as HIPAA, SOC 2, or GDPR.
• Strong GCP experience combined with working knowledge of another cloud or data platform.