Full Stack Sr. AI Engineer

As a Senior AI Engineer with strong full-stack capabilities, you will be joining the engineering team to work on multiple client-facing projects that involve AI, data, and web technologies. Your primary responsibility will be to work on a live production AI agent platform where you will own features end-to-end, from LLM pipeline design to polished frontend experiences. Key Responsibilities: - Designing and building AI agent pipelines, including multi-node LangGraph graphs - Implementing intent routing, multi-turn conversational context, session state management, and tool integrations - Developing multi-step reasoning pipelines and graph-based agent workflows - Building and maintaining Retrieval-Augmented Generation (RAG) systems - Designing vector search architectures, embedding pipelines, retrieval grounding, and chunking strategies - Implementing hallucination mitigation techniques and retrieval evaluation frameworks - Integrating and optimizing Large Language Models (LLMs) including OpenAI, Gemini, and Anthropic - Developing structured output workflows using JSON schemas - Creating effective prompt engineering strategies, few-shot examples, and context window management solutions - Designing, developing, and deploying end-to-end product features - Building scalable FastAPI backends and React/Next.js frontends - Implementing Server-Sent Events (SSE) streaming and REST API contracts - Owning LLM observability, including token usage logging, cost tracking, fallback detection, performance monitoring, regression test suites, and building evaluation pipelines and golden test suites - Collaborating directly with clients and stakeholders to understand business requirements - Translating requirements into scalable, maintainable software solutions - Keeping technical documentation, specifications, and test coverage aligned with product changes Qualifications Required: - Proficiency in LangGraph or equivalent graph-based agent frameworks, multi-step reasoning pipelines, tool orchestration, state management, and conversational workflows - Experience with end-to-end RAG pipeline design and implementation, vector databases such as Pinecone, Qdrant, pgvector, Weaviate, chunking strategies, retrieval optimization, and retrieval evaluation methodologies - Familiarity with OpenAI, Gemini, and Anthropic SDKs, prompt engineering, prompt optimization, structured JSON outputs, context window management, and multi-provider LLM integrations - Strong Python backend development skills using Python 3.12, FastAPI, Async Python, Pydantic, SQLite, PostgreSQL, Redis, and Pytest - Knowledge of React, Next.js, TypeScript, modern frontend architecture, API integration, and state management - Understanding of ML engineering fundamentals including evaluation pipelines, golden datasets, test suites, regression tracking, and model performance monitoring This job also requires expertise in GIS & Mapping, Data Visualization, Cloud & DevOps, and Product Thinking as mentioned in the additional details of the company. As a Senior AI Engineer with strong full-stack capabilities, you will be joining the engineering team to work on multiple client-facing projects that involve AI, data, and web technologies. Your primary responsibility will be to work on a live production AI agent platform where you will own features end-to-end, from LLM pipeline design to polished frontend experiences. Key Responsibilities: - Designing and building AI agent pipelines, including multi-node LangGraph graphs - Implementing intent routing, multi-turn conversational context, session state management, and tool integrations - Developing multi-step reasoning pipelines and graph-based agent workflows - Building and maintaining Retrieval-Augmented Generation (RAG) systems - Designing vector search architectures, embedding pipelines, retrieval grounding, and chunking strategies - Implementing hallucination mitigation techniques and retrieval evaluation frameworks - Integrating and optimizing Large Language Models (LLMs) including OpenAI, Gemini, and Anthropic - Developing structured output workflows using JSON schemas - Creating effective prompt engineering strategies, few-shot examples, and context window management solutions - Designing, developing, and deploying end-to-end product features - Building scalable FastAPI backends and React/Next.js frontends - Implementing Server-Sent Events (SSE) streaming and REST API contracts - Owning LLM observability, including token usage logging, cost tracking, fallback detection, performance monitoring, regression test suites, and building evaluation pipelines and golden test suites - Collaborating directly with clients and stakeholders to understand business requirements - Translating requirements into scalable, maintainable software solutions - Keeping technical documentation, specifications, and test coverage aligned with product changes Qualifications Required: - Proficiency in LangGraph or equivalent graph-base