Net2Source (N2S)Remote
Generative AI Engineer
United States
Full-time
1 week ago
$65 - $70 USD
H1B Sponsor Likely
Key skills
AI/ML engineeringLLMsRAG architecturesPython developmentvector databasescloud/serverless deploymentPythonAIMLGenerative AILLMFastAPIFlaskAWSServerlessLambdaCloud RunCloud FunctionsPerformance OptimizationCommunication
About this role
Net2Source (N2S) is seeking an experienced AI/ML Engineer to design and implement AI-assisted language generation solutions. This role focuses on Generative AI and RAG to produce automated draft messages within validation workflows.
Responsibilities:
- Design and implement LLM-based draft message generation systems
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines
- Apply prompt engineering and structured output formatting
- Implement safeguards to improve output accuracy and reduce hallucinations
- Integrate AI services into automated validation workflows
- Trigger draft generation at completion of validation runs
- Ensure reliable API communication between AI services and enterprise systems
- Build document ingestion, chunking, and embedding pipelines
- Implement vector search for contextual retrieval
- Deploy services using serverless platforms (Cloud Run, Cloud Functions, AWS Lambda, etc.)
- Develop scalable REST APIs (FastAPI/Flask)
- Implement logging, monitoring, and performance optimization
Requirements:
- 3+ years of AI/ML engineering experience
- Hands-on experience with LLMs and RAG architectures
- Strong Python development skills
- Experience with vector databases and document processing
- Experience deploying AI services in cloud/serverless environments