AI & LLM Engineer
First seen by Alion on Nov 13, 2026.
Role Overview :
Build and evaluate the intelligence layer of AI solutions for customer-management and Digital Experiences use cases. The Engineer develops agent, chatbot and voice-bot workflows using large language models, retrieval and tool integrations, with a focus on safe, measurable and operationally reliable behavior.
Key Responsibilities :
- Design, develop and iterate AI agents, chatbots, voice-bot workflows and agent-assist capabilities based on approved use cases and solution requirements.
- Implement LLM patterns including prompt design, retrieval-augmented generation (RAG), tool/function calling, conversation state and structured outputs.
- Integrate selected model and cloud platforms such as Gemini/Vertex AI, OpenAI or other approved services through maintainable interfaces.
- Build grounding, guardrails, refusal behavior, escalation paths, validation and human-in-the-loop controls appropriate to the use case and risk.
- Create repeatable evaluation datasets and tests; measure answer quality, task completion, groundedness, hallucination/error rates, latency and model cost.
- Collaborate with Solution Architecture, Software/Integration and Operations to connect knowledge sources, APIs, workflows, telephony/contact-center channels and business systems.
- Instrument solutions for observability and feedback; investigate failures and regressions and improve prompts, retrieval, orchestration or model choices.
- Document technical decisions, model/configuration changes, known limitations, test evidence and operational guidance for handover and governance review.
Qualifications & Experience :
- Bachelors degree in Computer Science, Engineering, Data Science or a related discipline, or equivalent practical experience.
- Hands-on experience building software or AI solutions with Python or a comparable language and integrating HTTP APIs.
- Practical familiarity with LLMs, prompt engineering, RAG, embeddings/vector search, tool calling and structured response formats.
- Experience with one or more approved cloud AI platforms or model APIs; exposure to conversational AI, voice bots or contact-center solutions is useful.
- Understanding of testing and evaluation for probabilistic systems, including grounding, safety, latency, reliability and cost considerations.
Core Competencies :
- Strong software engineering discipline, experimentation and analytical debugging.
- Security- and privacy-aware handling of prompts, data, tools and model outputs.
- Ability to explain model behavior, limitations and evaluation evidence to technical and operational partners.
Skills
Artificial Intelligence, LLM, Generative AI, Python, Conversational AI, Agentic AI, RAG, Prompt Engineering, VectorDB, LangChain