GenAI Software Engineer (Python / AWS Bedrock)
Scientec Consulting · Singapore
We are seeking a skilled Generative AI Software Engineer to design, develop and implement AI-powered applications and intelligent solutions. The successful candidate will work on developing and integrating Large Language Models (LLMs), building AI-driven applications and deploying scalable AI solutions to support business and operational needs. You will collaborate with software engineers, data scientists, solution architects and business stakeholders to transform AI concepts and use cases into production-ready applications.Working Hours: Mon-FriWorking Location: CentralSalary Package: Up to $11,000 (basic) + AWSJob Type: ContractKey Responsibilities1. Generative AI Application DevelopmentDesign, develop and implement Generative AI-powered applications and solutions using Large Language Models (LLMs).Build AI-enabled features such as intelligent chatbots, virtual assistants, conversational AI and automated content generation solutions.Develop and integrate LLM-based applications with enterprise systems, databases and business applications.Implement Retrieval-Augmented Generation (RAG) solutions to enable AI applications to retrieve and generate responses based on enterprise knowledge and data.Develop and optimise prompts, context management and AI workflows to improve response accuracy and application performance.2. AI Engineering & IntegrationIntegrate foundation models and AI services through APIs and SDKs.Work with frameworks and tools such as LangChain, LangGraph, LlamaIndex or similar technologies to develop AI-powered workflows and applications.Implement vector databases, embeddings and semantic search capabilities to support knowledge retrieval and AI applications.Develop backend services, APIs and microservices to support AI application integration.Evaluate and experiment with different LLMs, models and AI techniques to identify suitable solutions for business requirements.3. Software Engineering & Cloud DeploymentDevelop and maintain scalable backend applications and services using programming languages such as Python, Node.js or Java.Deploy and manage AI applications on cloud platforms such as AWS, Azure or Google Cloud.Implement CI/CD pipelines, automated testing, monitoring and application deployment practices.Optimise application performance, scalability, reliability and resource utilisation.Ensure AI applications comply with security, data privacy and enterprise technology standards.4. Testing & Continuous ImprovementEvaluate AI model performance, response quality, accuracy and reliability.Implement testing and evaluation frameworks to assess LLM outputs and identify potential hallucinations or inaccuracies.Monitor AI application performance and continuously improve prompts, workflows and retrieval mechanisms.Collaborate with cross-functional teams to troubleshoot technical issues and enhance AI solutions.Maintain technical documentation covering application architecture, integration, deployment and operational procedures.Job RequirementsDegree in Computer Science, Information Technology, Software Engineering, Artificial Intelligence or a related discipline.Minimum 3 years of relevant experience in software engineering, application development or AI engineering.Hands-on experience developing and implementing Generative AI applications using Large Language Models (LLMs).Strong programming skills in Python, Node.js, Java or other relevant programming languages.Experience integrating LLMs through APIs or SDKs, such as OpenAI, Azure OpenAI, AWS Bedrock, Anthropic or equivalent platforms.Good understanding of Prompt Engineering, Retrieval-Augmented Generation (RAG), embeddings and semantic search.Experience with AI development frameworks such as LangChain, LangGraph, LlamaIndex or similar.Familiarity with vector databases such as Pinecone, FAISS, Chroma, Weaviate or Milvus.Experience developing RESTful APIs, backend services and integrating AI solutions with enterprise systems.Exposure to cloud platforms such as AWS, Azure or Google Cloud.Strong understanding of software engineering principles, application architecture, testing and deployment practices.Good to Have:Experience with fine-tuning, model evaluation and optimisation of LLMs.Exposure to agentic AI, AI agents, multi-agent systems and tool/function calling.Experience with AWS Bedrock, Amazon SageMaker or other managed AI/ML services.Familiarity with Docker, Kubernetes, CI/CD and Infrastructure as Code.Knowledge of responsible AI, AI governance, data security and privacy.Experience implementing enterprise-grade AI solutions or deploying GenAI applications into production environments.By submitting your resume, you consent to the collection, use, and disclosure of your personal information per ScienTec’s Privacy Policy (scientecconsulting.com/privacy-policy).This authorizes us to:Contact you about potential opportunities.Delete personal data as it is not required at this application stage.All applications will be processed with strict confidence. Only shortlisted candidates will be contacted.Elane Yap Theng Yu- R1989397ScienTec Consulting Pte Ltd - 11C5781