What are the responsibilities and job description for the Generative AI Engineer position at NLB Services?
Job Overview
We are seeking a Senior AI / Generative AI Engineer with strong expertise in core Python development, Generative AI, and Agentic AI systems. This role focuses on designing, building, and deploying production-grade AI applications, including LLM-powered systems, RAG pipelines, and multi-agent workflows.
The ideal candidate will have hands-on experience building scalable AI services using FastAPI, implementing prompt engineering strategies, and developing agentic AI systems that can reason, plan, and interact with external tools and APIs.
Key Responsibilities
- Design, develop, and deploy AI/ML and Generative AI solutions using Python
- Build and operationalize LLM-based applications, including:
- Retrieval-Augmented Generation (RAG) pipelines
- Agentic AI workflows and multi-agent systems
- Develop scalable backend services using FastAPI / REST APIs
- Implement advanced prompt engineering strategies for improved model performance and reliability
- Design and build agent orchestration systems, including:
- Tool calling (APIs, databases, services)
- Memory management (short-term / long-term)
- Context handling and reasoning workflows
- Work with vector databases and embeddings to support semantic search and RAG architectures
- Implement best practices for:
- Model evaluation
- Monitoring and observability
- Performance optimization
- Collaborate with data engineering, platform, and product teams to productionize AI solutions
- Ensure scalability, security, and reliability of AI systems in production
- Mentor junior engineers and contribute to AI architecture and engineering standards
Mandatory Technical Skills
- Python (strong, production-level experience)
- FastAPI / REST API development
- Generative AI & Large Language Models (LLMs)
- Agentic AI systems (multi-agent, orchestration, tool usage)
- Prompt Engineering (advanced)
- RAG (Retrieval-Augmented Generation) architectures
- Vector databases & embeddings (e.g., Pinecone, FAISS, Weaviate)
- Strong understanding of:
- Machine Learning & Deep Learning fundamentals
- Data processing and feature engineering
Generative AI Frameworks & Tools
- LangChain
- LangGraph
- LlamaIndex
- Experience with:
- Agent frameworks (e.g., CrewAI, AutoGen, Semantic Kernel – preferred)
- LLM orchestration and chaining workflows
Cloud & MLOps (Required – at least one)
- AWS (SageMaker, Bedrock preferred)
- Azure AI / Azure OpenAI
- Google Cloud Platform (Vertex AI)
Additional (Nice to Have):
- CI/CD pipelines for ML systems
- Containerization (Docker, Kubernetes)
- ML pipelines / LLMOps practices
Experience Requirements
- 7 years of experience in AI / Machine Learning / Software Engineering
- 2 years of hands-on experience with Generative AI / LLM-based systems
- Strong, core experience in:
- Python development
- API-based system design (FastAPI)
- Building and deploying production AI systems
Nice to Have
- Experience building agentic AI systems in production
- Exposure to LLMOps / MLOps practices
- Experience designing scalable, distributed AI systems
- Strong communication and stakeholder collaboration skills
What This Role Emphasizes (Important)
- Heavy focus on hands-on Python FastAPI development
- Strong depth in Agentic AI (not just basic GenAI usage)
- Real-world experience with:
- Prompt engineering
- RAG pipelines
- LLM orchestration