Artificial Intelligence Engineer

Responsibilities:

AI Product Engineering & Deployment:

• Translate product requirements and user stories into production-grade AI solutions using AWS Bedrock, Lambda, ECS/EKS, and Databricks.
• Implement RAG pipelines with Delta tables, Unity Catalog, and Vector Search.
• Design and deploy multi-model agents that dynamically select between LLMs (Claude, GPT, Llama, Titan, etc.) based on task context, cost, and latency.
• Implement multi-agent orchestration frameworks enabling collaboration among specialized agents (e.g., data retriever, planner, summarizer, and action executor) for complex construction workflows.
• Own full lifecycle delivery — design, development, testing, deployment, monitoring, and maintenance.

Full-Stack & Backend Development:

• Build APIs, backend services, and agentic workflows using Python, FastAPI, LangChain, and AWS SDKs.
• Create reusable connectors and orchestration layers for multi-model agents (Claude, GPT, Llama, etc.).
• Develop front-end integrations for Teams and web SPAs via REST or GraphQL endpoints.

Data Engineering & Integration:

• Partner with Data Engineering to design robust ETL/ELT pipelines from enterprise systems to the Databricks Lakehouse.
• Ensure efficient data access, caching, and vectorization for low-latency AI response.
• Build tools to monitor and improve data quality, latency, and observability.

DevOps & Platform Automation:

• Use Terraform, AWS CDK, and GitHub Actions to automate infrastructure and deployments.
• Implement LLMOps: cost monitoring, latency optimization, usage analytics, and model versioning.
• Enforce security, governance, and access standards in line with enterprise policies.

Collaboration & Communication:

• Work closely with product managers, site AI engineers, and data scientists to iterate rapidly in Agile sprints.
• Communicate technical progress clearly to non-technical stakeholders; contribute to internal AI playbooks and templates.

Qualifications:

• 4-6 years of professional software development experience on AWS, with 2+ years focused on AI/ML engineering (LLMs, RAG, Bedrock, or similar). Strong coding proficiency in Python (LangChain, FastAPI, boto3) and solid experience with SQL, Databricks, and vector databases.
• Experience designing and deploying production systems using AWS Lambda, ECS/EKS, API Gateway, Step Functions, S3, CloudFront, and KMS.
• Strong foundation in CI/CD, IaC (Terraform/CDK), and GitHub Actions
• Experience training, retraining and performing transfer learning on ML models desirable.
• Bachelor’s in Computer Science, Engineering, Physics, or a related field; Master’s preferred.
• Prior hands-on work in construction or heavy process industries (manufacturing, oil & gas, chemicals) is a significant plus.
• Excellent collaboration and communication skills — able to work cross-functionally but not dependent on business-side facilitation.
• Integration & ETL skills: Foundational understanding of ETL/ELT design, Airflow or Databricks Workflows, and REST/GraphQL API development; proven collaboration with Data Engineering on source-to-lake and lake-to-agent pipelines.