Generative AI Engineer

UNISYNC SYSTEMS PTE. LTD.; Singapore; On-site; SGD 180,000 - 290,000; Full time

Job summary

UNISYNC SYSTEMS PTE. LTD. seeks an experienced Generative AI Engineer / Technical Lead to architect and deliver enterprise AI solutions, focusing on Generative AI, LLMs, RAG, AI agents and financial document intelligence.

You will lead AI engineering initiatives, design scalable backends, and integrate LLM platforms with enterprise systems. The role requires deep Python backend expertise, hands-on RAG/LLM experience, and strong leadership to mentor the engineering team and collaborate with

Qualifications

• 8+ years of software engineering experience with Generative AI focus
• Strong backend development and Python expertise
• Experience building RAG, LLM and AI-agent based apps
• Hands-on with LangChain/LangGraph or similar frameworks
• Understanding vector databases, embeddings and semantic search
• Experience with Weaviate/Pinecone/Qdrant or similar tech
• Experience with OpenAI/Claude/Llama or AWS Bedrock
• Proficient in FastAPI, REST APIs, microservices and scalable backends
• Knowledge of SQL, PostgreSQL, MongoDB, Redis
• Experience with AWS, Docker, Kubernetes and CI/CD
• Knowledge of AI evaluation, guardrails, prompts and security
• Strong analytical, problem-solving and communication skills

Responsibilities

• Design and develop Generative AI and RAG-based enterprise apps
• Develop AI agents and workflows using LangChain/LangGraph or equivalents
• Build retrieval solutions with embeddings, vector DBs, semantic search, reranking
• Create AI-powered financial document analysis and information extraction
• Integrate LLM platforms like OpenAI, Claude, Llama, AWS Bedrock
• Implement evaluation, observability, safety to reduce hallucinations
• Develop scalable backend services and APIs with Python, FastAPI, microservices
• Work with PostgreSQL, MongoDB, Redis, and vector databases
• Deploy with AWS, Docker, Kubernetes; follow CI/CD and testing practices
• Provide technical guidance and mentorship to engineers
• Collaborate with product/business teams to scale AI solutions

Skills

Generative AI

Python

RAG

AI-agent development

LangChain

LangGraph

Vector databases

Embeddings

Semantic search

OpenAI

Claude

Llama

AWS Bedrock

FastAPI

REST APIs

Microservices

PostgreSQL

MongoDB

Redis

AWS

Docker

Kubernetes

CI/CD

AI evaluation

Prompt engineering

Security

Tools

Weaviate

Pinecone

Qdrant

LangChain

Job description

Job Summary

We are looking for an experienced Generative AI Engineer / Technical Lead to design and develop enterprise AI solutions, with a focus on Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents and financial document intelligence.

The role involves developing scalable AI applications and backend services, integrating LLM technologies with enterprise systems, and providing technical leadership for AI engineering initiatives.

Key Responsibilities

• Design and develop Generative AI and RAG-based applications for enterprise and financial document use cases.
• Develop AI agents and agentic workflows using LangChain, LangGraph or similar frameworks.
• Build retrieval solutions using embeddings, vector databases, semantic search, reranking and contextual retrieval.
• Develop AI-powered solutions for financial document analysis, comparison, validation and information extraction.
• Integrate LLM platforms including OpenAI, Claude, Llama and AWS Bedrock.
• Implement AI evaluation, observability and safety mechanisms to improve response accuracy and reduce hallucinations.
• Develop scalable backend services and APIs using Python, FastAPI and microservices architecture.
• Work with PostgreSQL, MongoDB, Redis and vector databases.
• Deploy and manage applications using AWS, Docker and Kubernetes.
• Develop CI/CD pipelines and follow software engineering practices including testing, code quality and version control.
• Provide technical guidance and mentorship to engineering team members.
• Collaborate with product and business teams to translate requirements into scalable AI solutions.

Requirements

• Minimum 8 years of software engineering experience, including relevant experience in Generative AI.
• Strong hands-on experience in Python and backend development.
• Experience developing RAG, LLM and AI-agent based applications.
• Hands-on experience with LangChain, LangGraph or equivalent frameworks.
• Strong understanding of vector databases, embeddings and semantic search.
• Experience with Weaviate, Pinecone, Qdrant or similar technologies.
• Experience with OpenAI, Claude, Llama or AWS Bedrock.
• Experience with FastAPI, REST APIs, microservices and scalable backend systems.
• Good knowledge of SQL, PostgreSQL, MongoDB and Redis.
• Experience with AWS, Docker, Kubernetes and CI/CD.
• Knowledge of AI evaluation, prompt engineering, guardrails and security.
• Strong analytical, problem-solving and communication skills.

Preferred Experience

• Experience in financial services, investment management, insurance or financial document processing.
• Experience in KYC/AML, compliance or financial document intelligence.
• Knowledge of LangSmith, RAGAS, Arize Phoenix or similar AI evaluation tools.
• Experience with AWS Textract or document extraction technologies.