Project Role : Data Engineer
Project Role Description : Design, develop and maintain data solutions for data generation, collection, and processing. Create data pipelines, ensure data quality, and implement ETL (extract, transform and load) processes to migrate and deploy data across systems.
Must have skills : AWS Machine Learning
Good to have skills : Machine Learning (ML), Data Analytics, Amazon Web Services (AWS)
Minimum
18 year(s) of experience is required
Educational Qualification : 15 years full time education
Summary:
We are looking for a seasoned Principal Agentic AI Engineer with deep expertise in AWS cloud architecture, LLM-based intelligent systems, and agentic AI design patterns. This role involves architecting and deploying autonomous, multi-agent systems capable of reasoning, planning, acting, and collaborating within enterprise cloud environments.
As a Data Engineer, you will engage in the design, development, and maintenance of data solutions that facilitate data generation, collection, and processing. Your typical day will involve creating robust data pipelines, ensuring the integrity and quality of data, and implementing efficient ETL processes to migrate and deploy data across various systems. You will collaborate with cross-functional teams to understand their data needs and provide innovative solutions that enhance data accessibility and usability.
Roles & Responsibilities:
- Design and lead the development of scalable, resilient agentic AI systems.
- Integrate LLMs with enterprise APIs and data stores.
- Implement Retrieval-Augmented Generation (RAG) pipelines and tool-augmented agents.
- Ensure robust observability, fault tolerance, and CI/CD integration.
- Expected to be a Subject Matter Expert with deep knowledge and experience.
- Should have influencing and advisory skills.
- Engage with multiple teams and be responsible for team decisions.
- Expected to provide solutions to problems that apply across multiple teams, and provide solutions to business area problems.
- Facilitate workshops and discussions to gather requirements and feedback from stakeholders.
- Mentor junior team members to enhance their skills and knowledge in data engineering.
Professional & Technical Skills:
- Programming Languages: Python (primary), Go, Java, TypeScript
- Agentic AI Frameworks: LangGraph, CrewAI, AutoGen, LangChain, Semantic Kernel
- LLMs: OpenAI GPT, Anthropic Claude, Llama, Mistral, Falcon, AWS Bedrock models
- RAG Tools: Pinecone, FAISS, Weaviate, Qdrant, pgvector, AWS Kendra
- AWS Services: SageMaker, Bedrock, Lambda, ECS/EKS, Step Functions, S3, DynamoDB, Glue, Redshift, CloudFormation/Terraform
- LLMOps / CI-CD: GitLab CI/CD, AWS CodePipeline, MLflow, CloudWatch, Prometheus, Datadog, OpenTelemetry, Terraform
- Must To Have Skills: Proficiency in AWS Machine Learning.
- Good To Have Skills: Experience with Machine Learning (ML), Data Analytics, Amazon Web Services (AWS).
- Strong understanding of data pipeline architecture and design principles.
- Experience with ETL tools and frameworks for data processing.
- Proficiency in programming languages such as Python or Java for data manipulation.
Additional Information:
- 12+ years in software engineering, including 5+ years in AI/ML or data platform engineering.
- Proven track record in production-grade LLM or agentic system design.
- Strong foundation in data engineering and machine learning deployment.
- Excellent leadership and communication skills with the ability to mentor and influence technical direction.
- AWS Certified Machine Learning – Specialty
- AWS Certified Solutions Architect – Associate / Professional
- The candidate should have minimum 18 years of experience in AWS Machine Learning.
- This position is based at our Bengaluru office.
- A 15 years full time education is required.
