Senior AI Engineer

As a Senior AI Engineer at Uplevyl, you will play a crucial role in leading the design and deployment of AI-powered, agentic workflows that drive the future of personalized insights. Your main focus will be on vector search, retrieval-augmented generation (RAG), and intelligent automation, collaborating closely with full-stack engineers and product teams to bring scalable GenAI features into production. Key Responsibilities: - Design and implement RAG pipelines for semantic search, personalization, and contextual enrichment. - Build agentic AI workflows using Pinecone, LangChain/LangGraph, and custom orchestration. - Integrate LLM-driven features into production systems, balancing innovation with scalability. - Architect and optimize vector databases (Pinecone, FAISS, Milvus) for low-latency retrieval. - Work with structured/unstructured datasets for embedding, indexing, and enrichment. - Collaborate with data engineers on ETL/ELT pipelines to prepare data for AI applications. - Partner with backend and frontend engineers to integrate AI features into user-facing products. - Participate in Agile ceremonies (sprint planning, reviews, standups). - Maintain clear documentation and support knowledge sharing across the AI team. Required Qualifications: - 5+ years in AI/ML engineering or software engineering with applied AI focus. - Hands-on experience with RAG pipelines, vector databases (Pinecone, FAISS, Milvus), and LLM integration. - Strong background in Python for AI workflows (embeddings, orchestration, optimization). - Familiarity with agentic architectures (LangChain, LangGraph, or similar). - Experience deploying and scaling AI features on AWS cloud environments. - Strong collaboration and communication skills for cross-functional teamwork. Tech Stack: - AI Tools: Pinecone, LangChain, LangGraph, OpenAI APIs (ChatGPT, GPT-4/5), HuggingFace models - Languages: Python (primary for AI workflows), basic Node.js knowledge for integration - Cloud & DevOps: AWS (Lambda, S3, RDS, DynamoDB, IAM), Docker, CI/CD pipelines - Data Engineering: SQL, Python (Pandas, NumPy), ETL/ELT workflows, Databases (Postgres, DynamoDB, Redis) - Bonus Exposure: React, Next.js Preferred Skills: - Experience with embedding models, HuggingFace Transformers, or fine-tuning LLMs. - Knowledge of compliance frameworks (GDPR, HIPAA, SOC 2). - Exposure to personalization engines, recommender systems, or conversational AI.,