AI Engineer

Marlabs, a global AI and Digital Solutions Consulting firm, delivers intelligent solutions across AI, data, analytics, and product engineering. Since 2000, we have partnered with some of the largest healthcare, life sciences, financial services, and government organizations worldwide. As we continue to expand our global footprint, we have an exciting opportunity for a highly skilled AI Engineer to join our innovative and dynamic team.

AI Engineer | About You

As an AI Engineer, you will be responsible for designing, building, and deploying next-generation AI solutions that leverage Large Language Models (LLMs), agentic workflows, Retrieval-Augmented Generation (RAG), and modern AI orchestration frameworks. You will work closely with product, data, and engineering teams to develop intelligent applications that combine AI reasoning, enterprise data retrieval, workflow automation, and scalable backend architectures. The ideal candidate combines strong software engineering expertise with hands-on experience building production-grade AI systems, agent frameworks, and cloud-native AI services.

AI Engineer | Day-to-Day

• Design, develop, and deploy agentic AI solutions that integrate Large Language Models (LLMs), machine learning models, enterprise data sources, and backend services using frameworks such as LangChain, LangGraph, Semantic Kernel, and PydanticAI.
• Build multi-agent orchestration workflows, memory management systems, reasoning loops, and tool-calling architectures that support complex business processes and decision-making.
• Develop and maintain Retrieval-Augmented Generation (RAG) pipelines, vector databases, embeddings, and data ingestion frameworks using technologies such as Pinecone, Weaviate, or similar platforms.
• Implement AI observability, tracing, and evaluation frameworks using tools such as LangSmith, Langfuse, and custom evaluation pipelines to measure model accuracy, latency, reliability, cost, and overall system performance.
• Design and enforce AI governance practices, including guardrails, safety controls, prompt validation, testing strategies, and monitoring processes for non-deterministic AI outputs.
• Deploy, manage, and scale containerized AI services using Docker, Kubernetes, and cloud platforms while collaborating with engineering teams to ensure availability, performance, and operational excellence.

AI Engineer | Skills & Experience

• 5-8 years of software engineering or backend development experience, with at least 2-3 years of hands-on experience building AI, LLM, RAG, or Generative AI solutions in production environments.
• Strong expertise with AI orchestration frameworks such as LangChain, LangGraph, Semantic Kernel, CrewAI, PydanticAI, or similar agent-based development platforms.
• Hands-on experience designing and implementing RAG architectures, vector databases, embeddings, semantic search, and enterprise knowledge retrieval solutions using platforms such as Pinecone, Weaviate, Qdrant, or equivalent technologies.
• Strong development experience with Python, FastAPI, REST APIs, microservices, and cloud-native architectures, including deploying scalable AI applications in Azure, AWS, or GCP environments.
• Experience implementing AI observability, evaluation, guardrails, and testing frameworks, including tracing, prompt engineering, safety controls, model validation, latency optimization, and monitoring production AI systems.
• Preferred: Experience with Azure OpenAI, Azure AI Foundry, OpenAI APIs, containerization technologies (Docker, Kubernetes), and enterprise-scale AI solution delivery.