Generative AI Engineer

Helius Technologies Pte Ltd; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Helius Technologies Pte Ltd is seeking a Generative AI Engineer with hands-on Python development experience to build scalable GenAI solutions on cloud platforms, including AWS Bedrock. You will develop, test, and refine AI-driven applications, collaborate with cross-functional teams, and optimize prompts, embeddings, and retrieval workflows to improve model performance and user experiences.

The role emphasizes end-to-end implementation, from data handling to deployment, with a focus on robust,

Qualifications

• 2–3 years of experience in GenerativeAI.
• Proficient in Python for AI/ML model development, API integration and cloud deployment.
• Ability to craft, test and optimize AI prompts for LLM performance.
• Experience with vector databases and retrieval-augmented generation (RAG).

Responsibilities

• Develop, test, and deploy Generative AI models using LangChain, AWS Bedrock, and other frameworks.
• Use vector databases to enhance AI search, knowledge retrieval, and RAG for contextual responses.
• Design effective prompts to optimize AI outcomes.
• Implement search and retrieval techniques, including code ingestion and knowledge retrieval.
• Debug AI models and cloud-based solutions in AWS environments.
• Build and integrate front-end apps with Streamlit and back-end services with Python.
• Collaborate with cross-functional teams to test AI-driven solutions and gather feedback.
• Communicate complex AI concepts clearly to non-technical stakeholders.
• Contribute to team discussions with insights and solutions for AI challenges.

Skills

GenerativeAI

Python

Prompt engineering

Vector Databases

RAG techniques

LangChain

AWS Bedrock

Streamlit

APIs

Cloud deployment

Tools

AlloyDB

Aurora PostgreSQL

Job description

Required skills:

• 2 to 3 years of experience in GenerativeAI.
• Python programming skills, especially in AI/ML model development, API integration, and cloud-based deployment.
• Craft, test, and optimize AI prompts to improve LLM (Large Language Model) performance.
• Experience with Vector Databases (e.g. AlloyDB, Aurora PostgreSQL DB) – Knowledge of retrieval-augmented generation (RAG) techniques and efficient AI memory storage.

De ion: We are seeking a Generative AI Engineer with a strong technical background and hands‑on experience in Python programming. This role requires expertise in developing, implementing, and optimizing Gen AI-driven solutions using cloud platforms, particularly AWS services such as Bedrock.

As a GenAI Engineer, you will be at the forefront of integrating cutting‑off AI capabilities into scalable and efficient solutions that meet evolving business needs. Your primary focus will be to develop, test, and refine AI-driven applications, ensuring they are robust, efficient, and aligned with industry best practices.

Key Responsibilities:

• Develop, test, and deploy Generative AI models using LangChain, AWS Bedrock, and other AI frameworks.
• Leverage Vector Databases (e.g., AlloyDB, Aurora PostgreSQL DB) to enhance AI search efficiency, knowledge retrieval, and retrieval‑augmented generation (RAG) for improved contextual responses.
• Design effective prompts to optimize AI-generated outcomes through prompt engineering.
• Implement search and retrieval techniques, including code ingestion and knowledge retrieval to enhance AI performance.
• Debug AI models and cloud-based solutions independently, within AWS environments.
• Build and integrate front‑end applications using Streamlit and back‑end services using Python to create end‑to‑end AI applications.
• Collaborate with cross‑functional teams to test AI-driven solutions, gather feedback, and enhance system capabilities.
• Communicate complex AI concepts to non‑technical = ... ... … ... In content ...??? Maybe something.. APG ;
• Communicate complex AI concepts effectively to non‑technical stakeholders, ensuring clarity in AI adoption and implementation.
• Actively contribute to team discussions, providing insights and proposing solutions to AI-related challenges.