GenAI Engineer
Job Location:
Monthly Salary:
Experience Required:
Posted on:
Vacancies:
Job Summary
Hiring Alert GenAI Engineer (Immediate Joiners Only)
Job Overview
We are looking for a skilled GenAI Engineer with strong backend engineering expertise and hands-on experience in building production-grade AI/ML systems using modern GenAI stacks AWS services and RAG-based architectures.
Requirements
Key Skills Required
Core Engineering
- Strong proficiency in Python (async typing packaging unit testing)
- Strong understanding of Data Structures & Algorithms
- Experience with Microservices & Event-driven architecture
Cloud & AWS
- Hands-on experience with:
- Amazon Bedrock
- SageMaker
- S3 Lambda Step Functions
- CloudWatch IAM
- Amazon Bedrock
GenAI / LLM Stack
- RAG architectures (design indexing retrieval evaluation)
- LangChain / LangGraph
- Prompt engineering & evaluation techniques
- Guardrails (PII/Secrets redaction policy enforcement)
- HITL (Human-in-the-loop) workflows
- Vector DBs: pgvector / OpenSearch Vector
Data & Storage
- ETL pipelines using Pandas / Spark
- Databases: PostgreSQL DynamoDB NoSQL systems
DevOps & Engineering Practices
- Git CI/CD (GitHub Actions / Jenkins)
- Docker basic Kubernetes
- Logging monitoring tracing & observability
Bonus Skills
- ReactJS for full-stack prototypes
- Agentic workflows (tool calling task decomposition)
- SageMaker tuning / feature stores
- Prompt evaluation frameworks & cost monitoring dashboards
Required Skills:
Key Skills Required Core Engineering Strong proficiency in Python (async typing packaging unit testing) Strong understanding of Data Structures & Algorithms Experience with Microservices & Event-driven architecture Cloud & AWS Hands-on experience with: Amazon Bedrock SageMaker S3 Lambda Step Functions CloudWatch IAM GenAI / LLM Stack RAG architectures (design indexing retrieval evaluation) LangChain / LangGraph Prompt engineering & evaluation techniques Guardrails (PII/Secrets redaction policy enforcement) HITL (Human-in-the-loop) workflows Vector DBs: pgvector / OpenSearch Vector Data & Storage ETL pipelines using Pandas / Spark Databases: PostgreSQL DynamoDB NoSQL systems DevOps & Engineering Practices Git CI/CD (GitHub Actions / Jenkins) Docker basic Kubernetes Logging monitoring tracing & observability Bonus Skills ReactJS for full-stack prototypes Agentic workflows (tool calling task decomposition) SageMaker tuning / feature stores Prompt evaluation frameworks & cost monitoring dashboards
