AI - Integration Application Architect

Job summary: Design how AI models plug into our core systems and applicationsIntegrate LLMs and AI frameworks using tools like LangChain or Semantic KernelBuild RAG pipelines and work with vector databases where neededSet up APIs and microservices to connect AI into the broader tech stackEvaluate AI platforms for cost, performance, and compliance fitHandle data privacy, model risk, and monitoring for anything in productionWork closely with data science, engineering, and infrastructure teamsExperience : 8to 12Yrs Responsibilities: 8+ years in application/solution architecture3+ in AI/ML integrationHands on experience with LangChain, Hugging Face, TensorFlow, or similarExperience with LLM platforms: OpenAI, Anthropic, Azure OpenAI, AWS BedrockStrong grasp of RAG, vector databases (Pinecone, Weaviate, FAISS) Solid background in APIs, microservices, event driven architectureComfortable in AWSStrong coding skills in Python, JavaUnderstanding of MLOps/LLMOpsApplicant Notices & DisclaimersFor information on benefits, equal opportunity employment, and location-specific applicant notices, click here