Source description
About the role
Prompt engineering and orchestration.
Integrating models into production pipelines.
Designing and maintaining backend integrations and APIs for AI services.
Applying classical machine learning techniques where required.
Strong Python proficiency (core requirement).
Hands-on experience with LLM inferencing using OpenAI, Anthropic, and AWS Bedrock.
Knowledge of RAG architectures and vector search pipelines.
Experience with embeddings and vector databases such as FAISS, Pinecone, and Weaviate.
Experience with AWS AI/ML services including SageMaker, Bedrock, Lambda, API Gateway, S3, and DynamoDB.
Understanding of classical ML concepts including regression, classification, and anomaly detection.
Strong API design and backend integration skills.
More at Calsoft