Senior Full Stack Engineer GENAI & Rag

Title: Senior Full Stack Engineer – GenAI & RAG

Location: Santa Clara, CA-Onsite, Day 1 Mon-Fri

Duration: 12+ Months 

Job Description: Senior Full Stack Engineer – GenAI & RAG (12+ Years Experience)

Position Overview
We are seeking an accomplished Senior Full Stack Engineer with deep expertise in Generative AI, Retrieval-Augmented Generation (RAG), and modern full stack application development. The ideal candidate brings 12+ years of hands-on engineering experience, strong architectural skills, and a proven track record of building scalable, production-grade AI-driven systems.
This role involves leading end to end development of enterprise applications, designing and implementing GenAI solutions, integrating advanced LLM pipelines, and optimizing RAG architectures for real time and large scale workloads.
________________________________________
Key Responsibilities
GenAI / RAG Engineering
• Architect, design, and implement RAG pipelines using vector databases, embedding models, and retrieval frameworks.
• Build scalable GenAI microservices integrating LLMs (OpenAI, Azure OpenAI, Anthropic, Gemini, etc.).
• Fine tune, evaluate, and optimize LLM, embedding, and ranking models for enterprise scenarios.
• Implement document ingestion pipelines (PDFs, HTML, JSON, SQL, etc.) with chunking, embeddings, and metadata extraction.
• Develop evaluation frameworks for prompt engineering, grounding, hallucination reduction, and response consistency.
• Optimize latency, token usage, and retrieval accuracy for production deployment.
Full Stack Development
• Design and develop robust, scalable, and secure web applications (frontend + backend).
• Build RESTful and GraphQL services using Node.js, Python, Java, or similar.
• Develop responsive UI/UX using frameworks like React, Angular, or Vue.
• Integrate APIs, microservices, streaming pipelines, and cloud-native components.
• Implement CI/CD pipelines and ensure high availability, observability, and reliability.
Cloud & DevOps
• Deploy and manage applications on Azure / AWS / GCP.
• Work with container technologies (Docker, Kubernetes).
• Implement monitoring/logging using ELK, Prometheus/Grafana, App Insights, etc.
• Ensure infrastructure-as-code using Terraform, ARM, or CloudFormation.
Cross-Functional Collaboration
• Collaborate with AI researchers, product managers, architects, and business teams.
• Lead technical discussions, mentor junior engineers, and drive engineering best practices.
• Translate business requirements into scalable AI-driven technical solutions.
________________________________________
Required Skills & Experience
Technical Skills
• 12+ years of full stack hands-on development experience.
• Expertise in GenAI (LLMs, embeddings, vector search, RAG).
• Deep experience with: 
o Python / Node.js / Java
o React / Angular / Vue
o REST / GraphQL API development
• Strong understanding of: 
o Vector DBs (Pinecone, Chroma, Weaviate, FAISS, Elasticsearch)
o LLM orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel)
o Cloud AI services (Azure OpenAI, AWS Bedrock, Vertex AI)
• Solid experience with SQL & NoSQL databases (PostgreSQL, MongoDB, DynamoDB, Cosmos DB, etc.)
• Strong knowledge of microservices architecture, caching models, and distributed systems.
• Proficient in CI/CD pipelines, DevOps tools, and secure coding practices.