Software Engineer-

This role requires strong hands-on experience in Python, SQL, distributed data systems, AWS services, and enterprise-grade GenAI architectures with governed data access.

Key Responsibilities

• Design, build, and maintain scalable enterprise data platforms and data pipelines.
• Develop robust ETL/ELT pipelines for structured and unstructured data.
• Build secure, production-grade Retrieval-Augmented Generation (RAG) applications.
• Design document ingestion, chunking, embedding, indexing, and retrieval pipelines.
• Implement governed data access, metadata management, and security controls for GenAI applications.
• Develop scalable data orchestration workflows using Airflow or AWS Step Functions.
• Optimize data models and distributed processing frameworks for performance and scalability.
• Collaborate with AI, Data Science, Platform Engineering, Security, and Business teams to deliver enterprise AI solutions.
• Ensure compliance with security, governance, and regulatory requirements.

Required Skills

Core Technical Skills

• 10–15 years of Data Engineering / Platform Engineering experience.
• 3+ years of hands-on experience with GenAI, LLMs, and Retrieval-Augmented Generation (RAG).
• Strong programming skills in Python and SQL.
• Expertise in data modelling, ETL/ELT, and distributed data systems.
• Experience designing scalable enterprise data architectures.

AWS Expertise

Hands-on experience with:

• Amazon S3
• AWS Glue
• AWS Lambda
• Amazon EMR
• Amazon Redshift
• Amazon Kinesis
• AWS IAM

Data Orchestration

Experience with one or more:

• Apache Airflow
• AWS Step Functions

GenAI / RAG

Hands-on experience with:

• Enterprise RAG architecture
• LLM application development
• Embedding models
• Prompt engineering
• Vector search and semantic retrieval
• Document processing and indexing
• Secure and governed enterprise data access

Vector Databases

Experience with one or more:

• OpenSearch Vector Engine
• Pinecone
• FAISS
• Chroma

Preferred Skills

• LangChain
• LlamaIndex
• Amazon Bedrock
• OpenAI APIs
• Docker
• Kubernetes
• Terraform or CloudFormation
• CI/CD pipelines
• Data governance and security best practices

Domain Experience

Candidates with experience in Banking, Financial Services, Insurance, or other highly regulated industries will be preferred.

Nice to Have

• Knowledge of AI governance and Responsible AI principles.
• Experience with enterprise-scale data platforms.
• Exposure to MLOps and LLMOps practices.
• Strong stakeholder communication and solution design skills.