What The Role Offers

• Be part of an enterprise AI transformation team shaping the future of LLM-driven applications.
• Work with cutting-edge technologies in AI orchestration, RAG, and multi-agent systems.
• Opportunity to architect scalable, secure, and context-aware AI systems deployed across global enterprise environments.
• Collaborative environment fostering continuous learning and innovation in Generative AI systems engineering.

• Architect, implement, and optimize enterprise-grade RAG pipelines covering data ingestion, embedding creation, and vector-based retrieval.
• Design, build, and orchestrate multi-agent workflows using frameworks such as LangGraph, Crew AI, or AI Development Kit (ADK) for collaborative task automation.
• Engineer prompts and contextual templates to enhance LLM performance, accuracy, and domain adaptability.
• Integrate and manage vector databases (pgvector, Milvus, Weaviate, Pinecone) for semantic search and hybrid retrieval.
• Develop and maintain data pipelines for structured and unstructured data using SQL and NoSQL systems.
• Expose RAG workflows through APIs using FastAPI or Flask, ensuring high reliability and performance.
• Containerize, deploy, and scale AI microservices using Docker, Kubernetes, and Helm within enterprise-grade environments.
• Implement CI/CD automation pipelines via GitLab or similar tools to streamline builds, testing, and deployments.
• Collaborate with cross-functional teams (Data, ML, DevOps, Product) to integrate retrieval, reasoning, and generation into end-to-end enterprise systems.
• Monitor and enhance AI system observability using Prometheus, Grafana, and OpenTelemetry for real-time performance and reliability tracking.
• Integrate LLMs with enterprise data sources and knowledge graphs to deliver contextually rich, domain-specific outputs.

What You Need To Succeed

• Education: Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or related technical discipline.
• Experience: 5–10 years in AI/ML system development, deployment, and optimization within enterprise or large-scale environments.
• Deep understanding of Retrieval-Augmented Generation (RAG) architecture and hybrid retrieval mechanisms.
• Proficiency in Python with hands-on expertise in FastAPI, Flask, and REST API design.
• Strong experience with vector databases (pgvector, Milvus, Weaviate, Pinecone).
• Proficiency in prompt engineering and context engineering for LLMs.
• Hands-on experience with containerization (Docker) and orchestration (Kubernetes, Helm) in production-grade deployments.
• Experience with CI/CD automation using GitLab, Jenkins, or equivalent tools.
• Familiarity with LangChain, LangGraph, Google ADK, or similar frameworks for LLM-based orchestration.
• Knowledge of AI observability, logging, and reliability engineering principles.
• Understanding of enterprise data governance, security, and scalability in AI systems.

• Proven track record of building and maintaining production-grade AI applications with measurable business impact.
• Experience in fine-tuning Official notification