PYTHON DEVELOPER AND AI EXPERIENCE

Introduction: 100 % COMMUNICATION SKILL

This position is for a Python Developer with AI experience who is currently located in San Antonio. The ideal candidate should have a background in either FS or USAA or TEKsystems and must possess excellent communication skills. The main responsibilities will include working with Python, Fast API, Google Cloud Platform or AWS, and implementing AI solutions.

Responsibilities:

• Designing and developing FastAPI services for LLM calls
• Creating secure and versioned APIs using Python 3.x
• Utilizing cloud services on Google Cloud Platform or AWS for deployment
• Implementing datastores like Postgres/MySQL and Redis/ElastiCache/Memorystore
• Setting up CI/CD pipelines, containerization with Docker, and Infrastructure as Code (IaC) using Terraform
• Establishing testing culture, API specs, and observability
• Ensuring resiliency and performance tuning in distributed systems

Requirements:

Required Skills:

• 4-8+ years of software engineering experience with strong Python 3.x skills
• Experience with FastAPI or Flask for creating APIs
• Proficiency in Google Cloud Platform or AWS services like Cloud Run/GKE/Pub/Sub or Lambda/EKS/API Gateway/SQS
• Knowledge of datastores such as Postgres/MySQL and Redis/ElastiCache/Memorystore
• Familiarity with CI/CD tools like GitHub Actions/Cloud Build, containerization with Docker, and IaC with Terraform
• Experience with testing, API specs, and observability in distributed systems

Preferred Skills:

• Previous experience working with AI technologies
• Ability to handle streaming responses from LLM calls in FastAPI
• Knowledge of versioning APIs that expose AI functionality
• Experience in designing systems to handle malformed JSON responses from LLM APIs
• Understanding of normalizing responses from multiple AI providers into a consistent schema
• Expertise in storing prompt/response history in Postgres and designing appropriate schemas
• Skills in implementing service-to-service authentication between microservices calling AI endpoints
• Ability to debug and optimize AI endpoints for performance and cost efficiency