Skills – Mandatory -Python, Multi-LLM system, RAG, AWS Lambda, Amazon API Gateway, Claude models, Bedrock-hosted models(AWS Bedrock,
AWS Bedrock Knowledgebase)
Skills - Primary - Python, Multi-LLM system, RAG, AWS Lambda, Claude models, Bedrock-hosted models(AWS Bedrock, AWS Bedrock
Knowledgebase)
Skills - Good to have - AWS
Qualification Bachelor’s Degree
Total Experience- 5+ years
Relevant Experience 4+ years
Work Location - Kochi/TVM/Remote
Expected Date of Onboarding - Immediate
Job Purpose
We are seeking a hands-on AI Engineer to build, integrate, and operationalize Agenitc AI capabilities,
pre-dominantly with Gen AI. This is a core engineering role responsible for day-to-day implementation
of AI features using AWS-native tooling.
Job Description / Duties and Responsibilities
AI Engineering
• Build agentic solution with conversational agents at front end & agentic automation for data retrieval at the backend.
• Build Text to SQL AI capability
• Build Graph Database from SQL as well as unstructured data.
• Build and optimize RAG Pipelines, Graph RAG capabilities etc.
• Evaluate LLMs (Primarily AWS Bedrock based, additionally other Cloud and on-prem LLMs) for performance, scaling & cost perspectives.
• Knowledge on GPU based LLM installation/management is a plus
• Knowledge of MLOps and methodologies of model/agentic deployment is requisite.
Backend Development
Develop scalable services using:
• AWS OpenSearch Service
• AWS S3
• Amazon DynamoDB
• AWS CloudWatch
• Deploy via:
• AWS Lambda
• Amazon API Gateway
• Amazon CloudFront
Model Optimization
• Prompt engineering
• Retrieval tuning
• Latency optimization
• Output quality improvement
Adhere to the Information Security Management policies and procedures.
Job Specification / Skills and Competencies
Required Skills
• Hands-On experience in :
• GenAI application development
• RAG implementation
• Graph implementation
• LLM integration
• Strong AWS serverless experience
• Experience working with Bedrock-based architectures
• Ability to work independently in embedded teams
Nice to Have
• Experience with healthcare or sensitive data systems
• Exposure to AI evaluation frameworks
• Multi-model orchestration experience
• Bachelor’s or Master’s degree in Computer Science, or a related field.4
• Strong coding skills in Python and ML libraries such as TensorFlow, PyTorch, or scikit-learn.
• Experience with data preprocessing, feature engineering, and model lifecycle management.
• Proficiency in ML pipelines and deployment using MLflow, Docker, Kubernetes, or similar.
• Familiarity with cloud platform AWS and related AI/ML, LLM services.
• Strong understanding of statistics, probability, and data modeling.