AI Engineer
Role details
Job location
Tech stack
Job description
We are seeking an AI Engineer to design and build intelligent applications leveraging Generative AI technologies within an AWS ecosystem. This role involves developing enterprise-grade conversational systems, retrieval-driven AI solutions, and workflow automation capabilities.
You will work on integrating language models into scalable backend services, building data-aware assistants, and implementing automation pipelines that combine AI-driven and conventional approaches., * Architect and implement AI-powered solutions using AWS services such as Bedrock, Lambda, API Gateway, S3, DynamoDB, Step Functions, and CloudWatch.
- Develop conversational assistants that utilize internal data sources through retrieval-based techniques.
- Design and implement pipelines for document ingestion, segmentation, embedding generation, and semantic retrieval.
- Build and manage prompt strategies, structured tool usage, and multi-step execution flows for AI-driven tasks.
- Integrate AI services with enterprise systems, APIs, and databases.
- Develop backend components and service layers using Python and/or Node.js.
- Create automation workflows for operational tasks, selecting AI-based or rule-based approaches as appropriate.
- Perform testing, prompt optimization, and iterative improvements to enhance response quality and system performance.
- Implement observability practices including logging, monitoring, and fault handling.
- Collaborate with cross-functional teams to translate business requirements into technical implementations.
Requirements
- Minimum 2 years of experience in software development, backend engineering, or applied AI roles.
- Hands-on experience with AWS services relevant to application development and deployment.
- Experience building APIs, microservices, or workflow-driven systems.
- Solid understanding of large language model applications, prompt design, and conversational systems.
- Familiarity with retrieval-based architectures, embeddings, vector similarity search, and document-driven QA systems.
- Strong programming skills in Python.
- Working knowledge of Node.js or TypeScript is advantageous.
- Experience integrating external services using REST APIs, handling authentication, and working with structured data formats like JSON.
- Familiarity with version control systems, CI/CD pipelines, and software engineering best practices.
- Strong analytical and debugging capabilities.
Preferred:
- Experience working with Amazon Bedrock or similar managed LLM platforms.
- Familiarity with orchestration frameworks such as LangChain, LangGraph, CrewAI, or comparable tools.
- Exposure to agent-based or multi-step AI workflows.
- Experience with vector databases or search platforms (e.g., OpenSearch, Pinecone, FAISS).
- Understanding of serverless architectures and cloud-native design patterns.
- Basic knowledge of cloud security, IAM roles, and monitoring strategies.
- Experience in automating internal processes or business workflows.
Typical Projects
- Development of internal AI assistants and conversational interfaces
- Retrieval-based knowledge systems and enterprise search solutions
- Integration of AI capabilities into API-driven workflows
- Automation of routine business processes
- Implementation of early-stage agentic or multi-step intelligent systems