C2C careers
Location: Malvern, PA or Charlotte, NC (Onsite)
Duration: 8+ months
Experience Level: 12+ years
Description:
Develop and implement RAG pipelines including document ingestion, chunking, and embedding generation.
• Integrate LLM APIs (e.g., Azure OpenAI, AWS Bedrock) securely into applications and workflows.
• Configure and optimize vector databases for semantic and hybrid search performance.
• Build orchestration layers using frameworks like stated as per architecture
• Implement prompt templates and context management for consistent and accurate responses.
• Develop guardrails and validation logic to prevent unsafe or non-compliant outputs.
• Set up monitoring and logging for LLM performance, latency, and cost tracking.
• Optimize retrieval and response pipelines for scalability and low latency.
• Collaborate with Tech Lead and Architect to translate design into production-ready solutions.
• Create reusable components and SDKs for AI integration across multiple use cases.
Education: At least a bachelor’s degree (or equivalent experience) in Computer Science, Software/Electronics Engineering, Information Systems, or closely related field is required.
To apply for this job email your details to ganesh.g@itechus.net