Generative AI Engineer
First seen by Alion on Aug 31, 2026.
Job Description : Gen AI Engineer
Experience Required : 5+ Years
Work Mode : Remote
About the Role :
We are looking for an experienced Gen AI Engineer to design, build, and deploy production-grade Generative AI and Agentic AI systems. The ideal candidate has hands-on experience across the full Gen AI stack - from LLM orchestration and RAG pipeline architecture to fine-tuning, deployment, and monitoring - and is comfortable working independently in a remote-first environment.
Key Responsibilities :
- Design, build, and deploy Retrieval-Augmented Generation (RAG) pipelines, including semantic chunking, embedding generation, and hybrid retrieval strategies.
- Architect and implement Agentic AI workflows using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or Phidata for multi-step, tool-calling agent orchestration.
- Fine-tune and optimize LLMs using parameter-efficient techniques (PEFT, LoRA, QLoRA) for domain-specific use cases.
- Integrate LLM-powered applications (chatbots, copilots, automation agents) with vector databases (Pinecone, Qdrant, Neo4j, pgvector, Milvus, etc.) and graph databases where applicable.
- Build and maintain end-to-end AI pipelines (including on Databricks) for large-scale document ingestion, vectorization, and real-time inference.
- Deploy and manage AI systems on cloud platforms (AWS Bedrock/SageMaker, Azure OpenAI/AI Foundry, GCP Vertex AI) with secure, enterprise-grade configurations.
- Implement MLOps and CI/CD practices - containerization (Docker), orchestration (Kubernetes), experiment tracking (MLflow), and automated deployment pipelines (GitHub Actions).
- Monitor and evaluate production AI systems using tools such as LangSmith, RAGAS, DeepEval, or OpenTelemetry for reliability, drift detection, and performance tracking.
- Collaborate cross-functionally with product, data engineering, and (where applicable) front-end teams to integrate AI capabilities via REST APIs and microservices.
- Stay current with emerging Gen AI research, tools, and best practices, and evaluate their applicability to ongoing projects.
Required Skills & Experience:
- 5+ years of total IT experience, with significant hands-on experience in Generative AI / Agentic AI (typically 1.5 - 2+ years focused specifically on Gen AI).
- Strong programming proficiency in Python; working knowledge of SQL.
- Practical experience with Agentic AI frameworks: LangChain, LangGraph, CrewAI, AutoGen, Phidata, or similar.
- Experience with LLM providers: OpenAI, Anthropic (Claude), Google Gemini, Hugging Face models.
- Solid understanding of RAG architecture, embeddings, and semantic/hybrid search.
- Experience with vector and/or graph databases (Pinecone, Qdrant, Neo4j, Milvus, ChromaDB, FAISS, pgvector).
- Familiarity with LLM fine-tuning techniques (PEFT, LoRA, QLoRA).
- Working knowledge of cloud platforms (AWS, Azure, or GCP) - particularly their AI/ML services.
- Experience with Databricks for building end-to-end AI pipelines, large-scale data ingestion, and vectorization workflows.
- Experience with Docker, CI/CD pipelines, and basic MLOps practices.
- Strong analytical, problem-solving, and communication skills; ability to work independently in a remote setting.
Good to Have :
- Experience with computer vision (OpenCV, YOLO) or OCR pipelines.
- Familiarity with observability/evaluation tools (LangSmith, RAGAS, DeepEval, MLflow).
- Exposure to REST API/microservices integration (FastAPI, Node.js) for AI-powered web applications.
- Experience with Kubernetes for container orchestration.
- Prior experience in enterprise/regulated environments (secure LLM deployments, private endpoints, Key Vault, etc.).
- Relevant certifications (AWS, Azure AI, DeepLearning.AI, etc.).
Skills
Machine Learning, Python, Generative AI, RAG, Databricks