GenAI Engineer - RAG/LLM
First seen by Alion on Nov 6, 2026.
Job Summary:
We are looking for an experienced AI / GenAI Software Engineer with 5+ years of software engineering experience and strong expertise in Generative AI, NLP, Large Language Models (LLMs), Information Retrieval and RAG architectures.
The ideal candidate will have a strong production engineering mindset and experience taking AI solutions from experimentation to reliable, scalable enterprise applications.
Key Responsibilities:
- Design, develop and maintain production-grade AI/GenAI applications using Python.
- Develop enterprise solutions using LLMs, NLP, Prompt Engineering and Retrieval Augmented Generation (RAG).
- Design and implement RAG, hybrid retrieval and GraphRAG architectures.
- Work with vector search and information retrieval technologies, including OpenSearch or similar platforms.
- Develop APIs and AI services using modern Python frameworks and practices.
- Build automated AI evaluation pipelines to measure retrieval quality and LLM output quality.
- Write clean, maintainable and typed Python code using modern Python features.
- Develop comprehensive automated tests using pytest, mocking and unit/integration testing.
- Follow software engineering best practices including Git, merge requests, code reviews, CI/CD and code quality checks.
- Containerize and manage applications using Docker.
- Work across the SDLC and CRISP-DM lifecycle, converting AI experiments into deterministic and production-ready software.
- Collaborate with technical and non-technical stakeholders to understand requirements and deliver practical AI solutions.
- Continuously evaluate emerging GenAI technologies and identify opportunities for business/product improvement.
Mandatory Skills:
- 5+ years of professional software engineering experience
- Strong hands-on experience with Python
- Strong experience in Generative AI / LLMs
- Experience with NLP / Information Retrieval
- Hands-on experience with RAG
- Experience with Vector Search / Semantic Search
- Experience with Hybrid Retrieval
- Strong understanding of Prompt Engineering
- Experience developing production-grade AI applications
- Experience with pytest / automated testing
- Experience with Git, code reviews and software development lifecycle
- Experience with Docker / containerization
Preferred Skills:
- GraphRAG
- OpenSearch
- Pydantic
- Async Python / async-await
- FastAPI
- Automated LLM/RAG evaluation
- RAGAS / DeepEval / LangSmith or similar evaluation frameworks
- AWS Bedrock
- Azure OpenAI
- Model Context Protocol (MCP)
- Knowledge Graphs / Neo4j
Candidate Profile:
We are looking for someone who:
- Has a strong hands-on engineering mindset
- Can build AI solutions beyond prototypes and notebooks
- Understands how to take an AI experiment into production
- Has strong analytical and problem-solving abilities
- Can explain complex AI concepts to technical and non-technical stakeholders
- Learns quickly and adapts to the rapidly evolving GenAI ecosystem
- Takes ownership and works proactively
- Focuses on practical, scalable and reliable solutions
Important:
Candidates with only basic Python, generic Machine Learning, Data Science, Prompt Engineering or simple Chatbot experience may not be suitable.
Strong hands-on experience in RAG + LLM/GenAI + Python + production software engineering is highly preferred.
Skills
Artificial Intelligence, Python, Generative AI, RAG, NLP, Prompt Engineering, FastAPI, Neo4j, AWS Bedrock