Senior AI Full Stack Engineer

Senior AI Full Stack Engineer – GenAI & Agentic AI
Role Summary We are seeking a Senior AI Full Stack Engineer – GenAI & Agentic AI to design, build, and deploy production-grade AI applications combining modern full-stack engineering with Generative AI, LLMs, RAG, and Agentic AI . The role requires a strong hands-on engineer who can own solutions end-to-end—from frontend and backend development to LLM integration, agent orchestration, enterprise data integration, evaluation, and cloud deployment.
Key Responsibilities
- Design and develop end-to-end GenAI applications using Python, React/Next.js, APIs, databases, and cloud-native technologies.
- Build LLM-powered applications using commercial and open-source foundation models.
- Develop RAG pipelines including document ingestion, chunking, embeddings, vector search, retrieval, reranking, and response generation.
- Build AI agents and agentic workflows using tool/function calling, workflow orchestration, memory, reasoning patterns, and human-in-the-loop mechanisms.
- Develop backend services and APIs using Python, FastAPI and/or Node.js.
- Build responsive user experiences using React, Next.js, TypeScript/JavaScript .
- Integrate AI applications with enterprise databases, APIs, documents, SaaS applications, and knowledge repositories.
- Work with vector databases and search technologies such as pgvector, Pinecone, Weaviate, Milvus, Elasticsearch/OpenSearch or equivalent.
- Implement prompt management, structured outputs, context management, caching, session management, and model-routing capabilities.
- Develop LLM evaluation frameworks covering accuracy, relevance, groundedness, hallucination, safety, latency, and cost.
- Implement AI guardrails for prompt injection, sensitive-data exposure, inappropriate responses, and other AI security risks.
- Build observability and tracing for prompts, model responses, agent execution, token consumption, latency, failures, and cost.
- Deploy and operate applications on Azure, AWS, or GCP using Docker, Kubernetes/serverless technologies, and CI/CD.
- Optimize applications for scalability, reliability, performance, inference cost, and security .
- Conduct code reviews, establish engineering best practices, and mentor junior engineers.
- Work closely with product managers, AI/ML engineers, data scientists, architects, and business teams to move AI solutions from prototype to production .

Required Qualifications
- 6+ years of software engineering experience , with strong full-stack application development expertise.
- 2+ years of hands-on experience developing GenAI/LLM-based applications.
- Strong programming expertise in Python .
- Strong experience with React/Next.js and JavaScript/TypeScript .
- Hands-on backend development experience with FastAPI, Flask, Node.js , or similar frameworks.
- Practical experience integrating LLMs through APIs and model-serving platforms.
- Strong hands-on knowledge of RAG, embeddings, semantic search, vector databases, prompt engineering, and context management .
- Experience building AI agents or agentic workflows using frameworks such as LangGraph, LangChain, Semantic Kernel, LlamaIndex or equivalent.
- Strong experience designing and consuming REST APIs and microservices .
- Experience with relational and NoSQL databases, including PostgreSQL, MongoDB, Redis , or equivalent technologies.
- Experience deploying production applications on Azure, AWS, or GCP .
- Hands-on knowledge of Docker, CI/CD, Git and cloud-native development .
- Strong understanding of authentication, authorization, API security, data privacy, and secure application development.
- Demonstrated experience taking applications from design/prototype through production deployment and support .

Preferred Experience
- Experience with OpenAI/Azure OpenAI, Anthropic Claude, Google Gemini, Llama , or other leading foundation models.
- Experience building multi-agent systems, AI copilots, enterprise search, conversational AI, or autonomous workflow applications .
- Experience with model evaluation, LLM-as-a-judge techniques, human evaluation, and feedback loops.
- Knowledge of fine-tuning/SFT, preference data, synthetic data, and model evaluation .
- Experience with MCP/tool integration and enterprise agent architectures.
- Familiarity with AI observability and evaluation platforms.
- Experience with Kubernetes and Infrastructure-as-Code technologies such as Terraform.
- Understanding of Responsible AI, AI security, governance, and production LLMOps practices.