AI Engineer (LLM & RAG & QA) - W2 & locals only

Job Description

AI/ML Engineer (RAG & LLM & QA) - W2 & locals only

Location: Sunnyvale, CA (Hybrid)Experience: [3-7+ years]Visa Elegibility: USC/GC/TN/L2/H4-EADNo H1B/OPT/CPTWe're looking for an AI/ML Engineer to build and deploy production RAG systems and LLM-powered applications, including conversational experiences delivered over WhatsApp.Required Qualifications* Bachelor's or Master's in Computer Science, AI/ML, or a related field (or equivalent experience).* Hands-on RAG experience in production: embeddings, vector databases, hybrid search.* Strong Python (or Java or similar) with solid engineering fundamentals.* Experience with LLM APIs and open-source models.* Experience building REST APIs (FastAPI, Flask, Spring Boot).* Working knowledge of SQL/NoSQL databases, Docker, and cloud services.* WhatsApp integration experience is a big plusResponsibilities* Build and optimize RAG pipelines: ingestion, chunking, embeddings, indexing, retrieval, re-ranking, and generation.* Integrate LLMs (OpenAI, Claude, Llama, etc.) using LangChain, LlamaIndex, or custom orchestration.* Manage vector search infrastructure (Pinecone, Weaviate, Qdrant, FAISS, pgvector).* Develop chatbots and integrate them with the WhatsApp Business / Cloud API (webhooks, templates, session handling).* Implement prompt engineering, guardrails, and multi-turn context management.* Evaluate retrieval quality, accuracy, hallucination rate, latency, and cost.* Build and deploy scalable backend APIs on AWS, Azure, or GCP.* Handle user data and PII securely and in compliance with privacy requirements.Preferred (Big Plus)* WhatsApp integration experience: Cloud API, Twilio, Gupshup, or 360dialog, including opt-in and compliance requirements.* Other messaging channels (Slack, Telegram, SMS, Teams).* Agentic workflows, tool calling, and evaluation tools (RAGAS, LangSmith).* Fine-tuning (LoRA/PEFT) and MLOps experience.Please let me know if you are available and interested.