Generative AI Engineer

GenAI Engineer (Semantic Search & RAG Systems)

Location: Remote in India (to work in US Time zone)

Sesheng Company is looking for a skilled and driven GenAI Engineer to join our team on a contract basis. You will be instrumental in designing and deploying a cutting-edge semantic search capability to power our next generation of enterprise AI applications. This role is perfect for an engineer who thrives on building production-ready LLM-powered retrieval systems from the ground up.

As a GenAI Engineer, your primary focus will be on the end-to-end development of Retrieval-Augmented Generation (RAG) systems. You will leverage Amazon Bedrock, OpenSearch, and advanced vector embedding pipelines to deliver highly relevant and performant search and retrieval services.

Key Responsibilities

• Design and implement robust semantic search architectures utilizing Amazon Bedrock and OpenSearch (specifically k-NN indexing and vector embeddings).
• Build automated embedding pipelines for data ingestion and indexing using core AWS services like Lambda, S3, and API Gateway.
• Integrate multimodal embeddings (e.g., Titan Multimodal or similar models) to enable high-relevance search across both text and image data.
• Develop scalable REST APIs for handling semantic queries, sophisticated result ranking, and hybrid search (combining semantic relevance with filters).
• Collaborate closely with backend and data engineering teams to seamlessly integrate developed AI services into existing enterprise applications.
• Lead efforts in search relevance testing, optimization, and comprehensive technical documentation.

Required Skills & Experience

• Expert-level proficiency in Python and developing robust, scalable REST APIs.
• Proven experience working with Amazon Bedrock, OpenSearch, and various vector databases ( Weaviate, Pinecone, etc.).
• Deep technical understanding of LLM architectures, embeddings, and designing RAG pipelines.
• Practical experience with key AWS services including Lambda, API Gateway, S3, and Step Functions.
• Demonstrated ability to evaluate embedding quality, perform iterative tuning, and optimize search relevance.
• Strong problem-solving, communication, and collaboration skills, particularly in agile and fast-paced environments.

Nice-to-Have Qualifications

• Familiarity with PostgreSQL or experience using workflow automation tools like n8n.
• Experience successfully integrating and deploying AI features into production web or large-scale enterprise systems.

Sesheng Company is an Equal Opportunity Employer and values diversity. We encourage all qualified candidates to apply.