GenAI Engineer
First seen by Alion on Sep 1, 2026.
Role summary:
Were looking for a GenAI Engineer to build practical AI features for our Data & AI team. Youll work across Python services, large language models, retrieval workflows, prompt design, vector search, and agent-based integrations.
What youll do:
- Build GenAI applications using Python and established LLM and GenAI frameworks.
- Design retrieval-augmented generation (RAG) workflows, including document processing, chunking, embeddings, retrieval, and response generation.
- Develop and test prompts, system instructions, evaluation sets, and guardrails for business use cases.
- Work with vector databases and hybrid search approaches to improve grounding and response quality.
- Build agents that can call tools, use APIs, follow permissions, and complete defined tasks safely.
- Create API services and application components that connect GenAI workflows to product interfaces.
- Measure response quality, latency, cost, and failure cases, then improve the system through testing and iteration.
What youll bring:
- 4 - 5 years of relevant software, data, machine learning, or AI engineering experience.
- Strong Python skills and experience building production services or data workflows.
- Hands-on experience with LLMs, prompt engineering, RAG, embeddings, and vector databases.
- Experience with agent patterns, tool calling, function calling, or workflow orchestration.
- Working knowledge of GenAI frameworks such as LangChain, LlamaIndex, Semantic Kernel, or comparable tools.
- Ability to evaluate model outputs, handle failure cases, and communicate trade-offs clearly.
- Understanding of REST APIs, Docker, Git, and software testing practices.
Good to have:
- Experience with Azure OpenAI, AWS Bedrock, Hugging Face, or similar platforms.
- Exposure to data privacy, prompt injection risks, access control, and enterprise AI governance.
Skills
Machine Learning, Generative AI, Python, LLM, RAG, Prompt Engineering, VectorDB