Toyota is looking to solve the problem of developing GenAI software for their mobility and AI solutions
Requirements
Strong proficiency in Python programming, with practical experience using FastAPI for API development.
Expertise in prompt engineering to design, test, and refine prompts for LLMs.
Experience building AI agents and conversational AI systems using CAG methodologies.
Working knowledge of Retrieval-Augmented Generation (RAG) and its application in AI solutions.
Hands-on experience with vector databases such as Pinecone, Weaviate, or similar platforms.
Familiarity with scoring and ranking techniques for large language model outputs.
Solid understanding of AWS cloud infrastructure components including IAM, Lambda, S3, and EC2.
Responsibilities
Build and maintain RESTful APIs with Python (FastAPI; OpenAI/Bedrock SDKs as clients), containerized and deployed on AWS ECS Fargate.
Design clean contracts and versioned APIs; document with OpenAPI/Swagger.
Integrate with AWS Bedrock and other GenAI services to enable RAG and knowledge-base queries.
Work with vector databases (e.g., Pinecone, Weaviate, OpenSearch/Elasticsearch vector) for semantic search and retrieval.
Implement robust API clients for AI endpoints, including auth, throttling, retries, and error handling.
Configure API Gateway for secure routing, throttling, authentication/authorization.
Build CI/CD pipelines (GitHub Actions, Jenkins, or CodePipeline) for automated build/test/deploy; use GitHub/GitLab and artifact repos (e.g., Artifactory).
Other
Green Card, US Citizen
3 years of experience (preferred)
No travel required
9 AM to 5 PM shift timings
Excellent collaboration skills within agile, cross-functional teams.
