Exl Service
Agentic AI Data Engineer
Job description
Agentic AI Data Engineer
Role Overview
Total Experience required : 5-10 Years
We are seeking a highly skilled Agentic AI Data Engineer to design, build, and optimize intelligent, autonomous data systems that power next-generation AI applications. This role blends data engineering, machine learning infrastructure, and emerging agent-based AI frameworks to enable scalable, self-orchestrating pipelines and decision-making systems.
You will work at the intersection of data platforms, large language models (LLMs), and cloud-native architectures—building systems that can reason, act, and adapt autonomously.
Key Responsibilities
Design and implement agentic AI systems that autonomously orchestrate data workflows and decision pipelines
Build scalable data pipelines for structured and unstructured data (batch + real-time)
Develop and manage LLM-powered applications using retrieval-augmented generation (RAG), tool use, and multi-agent frameworks
Integrate AWS AI/ML services into production-grade architectures
Develop and optimize data lakes, warehouses, and lakehouse architectures
Build APIs and microservices to expose AI/ML capabilities
Ensure data quality, governance, and security across pipelines
Collaborate with data scientists, ML engineers, and product teams to deploy AI solutions
Implement monitoring, logging, and observability for AI agents and pipelines
Optimize cost and performance of cloud-based AI workloads
Required Technical Skills
Cloud & AWS Ecosystem
Strong experience with AWS services, including:
Amazon S3, Glue, Lambda, Step Functions
Amazon Redshift / Athena
Amazon SageMaker (training, deployment, pipelines)
Amazon Bedrock (foundation models, agents, knowledge bases)
AI/ML & Agentic Systems
Experience with LLMs and generative AI systems
Hands-on with agent frameworks (e.g., multi-agent orchestration, tool calling, planning systems)
Familiarity with AgentCore / agent orchestration platforms
Understanding of RAG architectures, embeddings, and vector databases
Experience with model deployment, inference optimization, and prompt engineering
Data Engineering
Strong proficiency in Python and SQL
Experience with ETL/ELT tools and frameworks
Distributed data processing (Spark, PySpark, or similar)
Streaming technologies (Kafka, Kinesis, or similar)
Data modeling and schema design
Data & AI Infrastructure
Experience with vector databases (e.g., Pinecone, FAISS, OpenSearch)
Knowledge of data lakehouse architectures (Delta Lake, Iceberg, Hudi)
Containerization (Docker) and orchestration (Kubernetes)
CI/CD for ML and data pipelines
Preferred Qualifications
Experience building autonomous AI agents for enterprise use cases
Knowledge of multi-agent collaboration systems and planning algorithms
Familiarity with LangChain, LlamaIndex, or similar frameworks
Experience with MLOps and LLMOps practices
Understanding of graph-based workflows and knowledge graphs
Exposure to real-time AI systems and event-driven architectures
Soft Skills
Strong problem-solving and system design skills
Ability to work in fast-paced, evolving AI environments
Effective communication and cross-functional collaboration
Curiosity and adaptability to emerging AI technologies
Education & Experience
Bachelor’s or Master’s degree in Computer Science, Engineering, or related field
4+ years of experience in data engineering or ML engineering
Hands-on experience with production-grade AI/ML systems
Nice-to-Have
Experience with reinforcement learning or planning systems
Background in distributed systems design
Contributions to open-source AI/data projects
Certifications in AWS (e.g., Solutions Architect, Machine Learning Specialty)
What You’ll Build
Autonomous data pipelines that self-heal and optimize
AI agents capable of reasoning over enterprise data
Scalable LLM-powered applications integrated with business workflows
Intelligent systems that move beyond automation into decision-making