Gen AI Engineer
First seen by Alion on Aug 24, 2026.
Gen AI Engineer RAG, Agentic AI & End-to-End Deployment
We are looking for a hands-on Gen AI Engineer who can design, build, deploy, and continuously improve production-grade AI solutions. The ideal candidate should have strong experience across RAG, AI Agents, LLMs, vector databases, Python, FastAPI, cloud deployment, and MLOps/LLMOps.
Key Responsibilities :
- Design and build production-grade RAG pipelines, including document ingestion, preprocessing, chunking, metadata enrichment, embeddings, vector search, retrieval, and re-ranking.
- Develop strategies to improve retrieval quality, relevance, grounding, and response accuracy.
- Design and implement single-agent and multi-agent AI systems capable of reasoning, tool usage, planning, and task execution.
- Own the complete AI solution lifecycle : data pipeline, RAG/agent development, evaluation, deployment, monitoring, and optimization.
- Build scalable APIs and backend services using Python and FastAPI.
- Deploy AI applications in cloud or on-premise environments with a focus on scalability, reliability, security, and maintainability.
- Build and maintain CI/CD pipelines with automated testing and evaluation of AI/agent outputs.
- Implement monitoring, logging, and observability for latency, cost, accuracy, quality, drift, failures, and user feedback.
Tech Stack & Requirements :
- Strong hands-on experience with Python and FastAPI.
- Deep expertise in RAG (Retrieval-Augmented Generation).
- Vector databases : Pinecone, Weaviate, FAISS, Chroma, or pgvector.
- AI Agent frameworks : LangChain, LangGraph, CrewAI, AutoGen, or Semantic Kernel.
- Experience with Docker, Kubernetes, and cloud platforms (AWS/Azure/GCP).
- Experience deploying at least one AI solution into a production environment.
Qualifications :
- Bachelor's or Master's degree in Computer Science, Engineering, AI/ML, or a related field.
- 3-8+ years of experience in AI/ML engineering or software engineering with strong Python development.
Skills
Machine Learning, Python, Generative AI, RAG, Cloud Computing, FastAPI, Artificial Intelligence