Senior Applied AI/LLM Engineer
First seen by Alion on Oct 21, 2026.
Role : Senior Applied AI / LLM Engineer
Job Summary :
We are looking for a Senior Applied AI / LLM Engineer to develop and integrate Large Language Model (LLM) - powered capabilities into production applications and business workflows.
The role focuses on applying frontier AI models to real-world products, building agentic solutions, and ensuring the reliability, security, and performance of enterprise AI applications.
Key Responsibilities :
- Design and develop LLM - powered applications, AI agents, and services using models such as Claude, GPT, and Gemini.
- Integrate LLM capabilities into existing production applications, APIs, and business workflows using Python.
- Build agentic workflows, tool integrations, MCP - based solutions, and automation capabilities.
- Develop and maintain LLM evaluation frameworks to measure accuracy, reliability, latency, and cost.
- Assess existing machine learning and model - based solutions to identify opportunities for enhancement or migration to frontier models.
- Implement AI guardrails, personally identifiable information (PII) protection, audit trails, and security controls for enterprise and customer - facing applications.
- Monitor production AI behavior, identify failure patterns, and improve prompts, workflows, and model performance.
- Collaborate with Product, Engineering, Technology, and Operations teams to identify and deliver valuable AI use cases.
Required Skills and Experience :
- 6+ years of software engineering experience, including strong recent experience in Applied AI and LLM engineering.
- Strong proficiency in Python and backend/API development.
- Proven experience deploying LLM - powered features in production environments.
- Hands - on experience with OpenAI, Anthropic, Gemini, or similar frontier models.
- Strong understanding of prompt engineering, Retrieval - Augmented Generation (RAG), tool/function calling, AI agents, and LLM evaluation.
- Experience developing production - grade APIs, services, and integrations.
- Strong understanding of AI security, privacy, and enterprise guardrails.
- Ability to work with existing production codebases and develop new AI capabilities from the ground up.
Preferred Skills :
- Experience with Model Context Protocol (MCP) servers, integrations, and AI agents.
- Experience migrating traditional machine learning or model - based solutions to LLM - based approaches.
- Familiarity with LLM observability and evaluation frameworks.
- Experience working in regulated environments involving PCI, SOX, or similar requirements.
- Familiarity with AI development tools such as Claude Code, Kiro, Cursor, or similar platforms.
Ideal Candidate Profile :
The ideal candidate is a strong software engineer with hands - on experience delivering LLM - powered features in production.
They should understand how to integrate AI into real - world products, combine software engineering with AI evaluation, and prioritize reliability, security, privacy, and enterprise - grade controls.
Skills
Generative AI, LLM, Python, Agentic AI, Prompt Engineering, RAG, Artificial Intelligence, GPT, Claude