Gen AI Lead

- We are looking for a Generative AI Tech Lead and Developers to provide technical leadership and architectural direction for building and operating production-grade GenAI solutions on AWS. This role combines hands-on development, solution architecture, team mentorship, and operational ownership. - Team will own end-to-end delivery of GenAI platforms using Python, AWS Bedrock (Agent Core SDK), AWS Strands SDK, and modern DevOps and observability practices, ensuring scalability, security, reliability, and cost efficiency. - Solid understanding of LLMs(Anthropic (Claude LLM)), embeddings, prompts, tokens, latency, cost factors - Practical experience with RAG architectures, vector stores, and grounding strategies - Ability to select and justify model choices (open-source vs proprietary) - Experience supporting real-world use cases, not just POCs or demos - Experience in AWS bedrock platform using Python, Strands SDK Multi-Agents, LangGraph/CrewAI

Key Responsibilities Generative AI Development

- Design and implement Generative AI applications using AWS Bedrock, including:

o Bedrock Agent Core SDK o Foundation Models (FM) integration oPrompt engineering and agent orchestration

- Build AI workflows using AWS Strands SDK for scalable model execution and orchestration - Develop and maintain reusable AI components, APIs, and services in Python - Optimize model performance, latency, and cost for production workloads

AWS-Native Application Development

- Design and develop cloud-native applications on AWS using:

o AWS Lambda, ECS/EKS, EC2 o API Gateway / Application Load Balancer o S3, DynamoDB, Aurora, OpenSearch

- Implement secure IAM roles and policies aligned with least-privilege principles - Build event-driven and microservices-based architectures

DevOps & CI/CD

- Design and maintain CI/CD pipelines using tools such as: - AWS CodePipeline / CodeBuild / CodeDeploy o GitHub Actions / GitLab CI (as applicable) - Infrastructure as Code (IaC) using: - AWS CloudFormation / CDK / Terraform - Automate build, test, deployment, and rollbacks for GenAI workloads

Observability & Operations

- Implement end-to-end observability for AI and application workloads: - Amazon CloudWatch (logs, metrics, alarms) o AWS X-Ray tracing o Custom metrics for model behavior and performance - Monitor: - Model response latency o Token usage and cost o Error rates and failure scenarios - Participate in incident management, root cause analysis, and system optimization

Security, Governance & Compliance

- Ensure secure handling of data used in AI workflows - Implement: - Encryption at rest and in transit o Secure secrets management (AWS Secrets Manager / Parameter Store) - Follow enterprise standards for: - Data privacy o AI governance o Responsible AI usage

Required Skills & Qualifications Technical Skills (Must Have) •Python (advanced proficiency)

- Hands-on experience with:

o AWS Bedrock o AWS Bedrock Agent Core SDK o AWS Strands SDK

- Strong knowledge of AWS services and cloud-native design patterns - Experience building and deploying applications natively on AWS - CI/CD pipeline implementation and maintenance - Observability and monitoring in production environments

Preferred Skills (Good to Have)

- Experience with: - LLMs, RAG (Retrieval Augmented Generation) - Vector databases and embeddings - Knowledge of containerization: - Docker, Kubernetes (EKS) - Familiarity with MLOps or Model Lifecycle Management - Experience with cost optimization for AI workloads - Understanding of ethical AI and responsible AI principles

Please share resume suchi.srivastava@birlasoft.com with Details:

Current CTC:

Expected CTC:

Notice period:

Total Gen Ai Exp:

AWS Bedrock Exp:

SDK/ Agen Rock Exp:

Python Engineering Exp: