Senior AI Engineer (Python / LLM / RAG / AI Agents)
First seen by Alion on Oct 30, 2026.
We are looking for an experienced Senior AI Engineer with strong Python development skills and hands-on experience designing, building, and deploying production-ready generative AI solutions.
The ideal candidate has a strong software engineering background combined with practical expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, and AI-powered applications.
Experience with TypeScript, Next.js, or React is a plus but is not required for candidates with exceptional AI engineering expertise.
Key Responsibilities
Design, develop, and deploy AI-powered applications and backend services using Python.
Build and maintain LLM integrations with providers such as OpenAI, Azure OpenAI, and Anthropic.
Design and implement RAG pipelines, including document processing, embeddings, retrieval, and context management.
Develop AI agents, tool-calling workflows, and multi-step LLM orchestration.
Build APIs and backend services for integrating AI capabilities into web applications.
Evaluate and optimize LLM outputs, reliability, latency, and operational costs.
Implement monitoring, logging, error handling, and production-ready AI workflows.
Collaborate with frontend and full-stack developers to integrate AI services into customer-facing products.
Required Skills
Strong professional experience in Python and backend software engineering.
Hands-on experience integrating LLM APIs into real-world applications.
Practical knowledge of RAG architectures, embeddings, and semantic search.
Experience with AI orchestration frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
Understanding of AI agent architectures, tool calling, and structured outputs.
Experience designing and building REST APIs and asynchronous backend services.
Proven experience deploying and maintaining AI solutions in production.
Strong understanding of software architecture, scalability, and system reliability.
Nice to Have
Experience with FastAPI or similar Python backend frameworks.
Knowledge of vector databases such as pgvector, Pinecone, Weaviate, or Qdrant.
Experience with agent orchestration frameworks such as LangGraph.
Experience with Azure AI services and cloud-native deployments.
Familiarity with Docker, CI/CD, and cloud infrastructure.
Experience with LLM evaluation, observability, and prompt optimization.
Knowledge of TypeScript, Next.js, React, or Vercel AI SDK.
Ideal Candidate
A senior Python engineer with proven experience delivering production AI solutions, capable of owning the AI backend architecture, building reliable LLM-powered services, and integrating them into modern web products.