Gen AI Engineer – AWS

Job Description Position: Gen AI Engineer – AWS Location: Bangalore (Work from Office) Notice Period: Not more than 30 days Job Summary We are seeking a highly skilled Gen AI Engineer – AWS to architect, build, and optimize next-generation GenAI-powered applications leveraging Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) pipelines. The ideal candidate will combine strong software engineering and cloud architecture expertise with a deep understanding of AI/ML systems to deliver scalable, secure, and high-performing GenAI solutions for enterprise use cases, including technical documentation, maintenance, and support workflows . This role involves designing advanced RAG architectures, fine-tuning LLMs, implementing microservices, and maintaining continuous evaluation frameworks — all while ensuring enterprise-grade compliance, observability, and operational efficiency on AWS infrastructure. Key Skills GenAI, LLMs, RAG, LangChain, Prompt Engineering, Fine-tuning, OpenAI, Anthropic, Amazon Bedrock, HuggingFace Transformers, Pinecone, FAISS, Milvus, Weaviate, Elasticsearch, Semantic Search, Vector Databases, G-Eval, QAG Scorer, MLflow, Prometheus, DataDog, CloudWatch, FastAPI, Flask, GraphQL, RESTful APIs, OAuth2, JWT, Docker, Kubernetes, Terraform, AWS CDK, CloudFormation, IAM, KMS, VPC, S3, CloudTrail, CI/CD, GitHub Actions, CodePipeline, MLOps, Data Modeling, Metadata Tagging, Schema Design, Multi-modal Retrieval, Enterprise GenAI Solutions, AWS Cloud Architecture, Compliance & SecurityRoles and Responsibilities Architect and build GenAI-powered applications using LLMs and advanced RAG pipelines for technical documentation, maintenance, and enterprise support workflows. Design and implement retrieval-augmented generation (RAG) systems leveraging vector databases and semantic search to enhance contextual information retrieval. Integrate and fine-tune LLMs (OpenAI, Anthropic, Amazon Bedrock, HuggingFace, etc.) for domain-specific applications and continuous improvement cycles. Develop and maintain evaluation frameworks for LLM outputs — assessing relevancy, faithfulness, summarization quality, and contextual accuracy . Build and deploy scalable and secure microservices and APIs (REST/GraphQL) using FastAPI/Flask for GenAI workflows. Collaborate cross-functionally with product, domain, and platform teams to define requirements and deliver innovative, production-ready GenAI solutions. Implement monitoring and observability using tools like Prometheus, MLflow, CloudWatch, and DataDog to ensure model reliability and quality assurance. Ensure security and compliance through best practices in IAM, KMS, VPC endpoints, encryption, and audit trail management. Leverage AWS DevOps practices (CodePipeline, CDK, Terraform, CloudFormation) for automated deployment, scaling, and lifecycle management of GenAI services. Stay up to date with emerging GenAI frameworks, architectures, and tools to continually enhance solution quality and performance. Requirements Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or related field. 5+ years of hands-on experience in AI/ML application development, with at least 2+ years focused on GenAI and LLM systems . Proven expertise in GenAI frameworks — LangChain, HuggingFace, Amazon Bedrock, OpenAI, and Anthropic models. Experience designing and deploying RAG architectures using vector databases such as Pinecone, FAISS, or Milvus. Strong skills in Python , API development (FastAPI/Flask) , and containerization (Docker, Kubernetes) . Practical knowledge of AWS cloud services , security , and DevOps pipelines (Terraform, CDK, CloudFormation). Experience with monitoring and evaluation tools — G-Eval, Prometheus, MLflow, or similar. Familiarity with multi-modal retrieval systems integrating text, image, and telemetry data. Prior experience in regulated domains (aviation, manufacturing, healthcare) with compliance and audit requirements is a plus. Exposure to MLOps practices — model deployment, rollback, versioning, and lifecycle management. Strong problem-solving skills, architectural thinking, and ability to translate research into production-ready systems. Requirements GenAI, LLMs, RAG, LangChain, Prompt Engineering, Fine-tuning, OpenAI, Anthropic, Amazon Bedrock, HuggingFace Transformers, Pinecone, FAISS, Milvus, Weaviate, Elasticsearch, Semantic Search, Vector Databases, G-Eval, QAG Scorer, MLflow, Prometheus, DataDog, CloudWatch, FastAPI, Flask, GraphQL, RESTful APIs, OAuth2, JWT, Docker, Kubernetes, Terraform, AWS CDK, CloudFormation, IAM, KMS, VPC, S3, CloudTrail, CI/CD, GitHub Actions, CodePipeline, MLOps, Data Modeling, Metadata Tagging, Schema Design, Multi-modal Retrieval, Enterprise GenAI Solutions, AWS Cloud Architecture, Compliance & Security