Senior Gen AI Engineer / Developer

TANGSPAC CONSULTING PTE LTD; Singapore; On-site; SGD 180,000 - 280,000; Full time

Job summary

TANGSPAC CONSULTING PTE LTD is seeking a Senior Gen AI Engineer in Singapore to design, build, and operationalise enterprise‑grade AI solutions. You will work across LLM engineering, backend microservices, and orchestration frameworks to deliver intelligent automation, conversational AI, and next‑generation decisioning capabilities.

You will collaborate with Data, Cloud, Product, and Engineering teams to deliver scalable, compliant, and high‑impact AI solutions, evaluate emerging technologies,

Qualifications

• Proficiency in Python for AI/ML engineering, model orchestration, and data workflows.
• Experience building and consuming RESTful APIs with authentication, versioning, and performance tuning.
• Practical experience with LangChain for LLM orchestration and tool-calling.
• Familiarity with LangGraph for building agentic workflows, stateful graph-based reasoning, and multi-step automation.
• Understanding of vector databases (FAISS, Milvus, Pinecone) and RAG architectures.

Responsibilities

• Build and deploy Gen AI applications using LLMs, embeddings, vector databases, and retrieval-augmented generation (RAG).
• Create Python pipelines for model fine-tuning, evaluation, inference, and data processing.
• Use LangChain and LangGraph to orchestrate multi-step AI workflows, agentic systems, and complex reasoning pipelines.
• Implement secure API gateways, model governance, monitoring, and performance optimisation for production AI workloads.
• Partner with Data, Cloud, Product, and Engineering teams to deliver scalable, compliant, and high-impact AI solutions.
• Evaluate emerging AI technologies and contribute to architectural decisions for enterprise AI platforms.

Skills

Python

RESTful APIs

LangChain

LangGraph

Vector databases

RAG architectures

Tools

FAISS

Milvus

Pinecone

Job description

A Financial Institution is looking for a Senior Gen AI to design, build, and operationalise enterprise‑grade AI solutions. You will work across LLM engineering, backend microservices, and orchestration frameworks to deliver intelligent automation, conversational AI, and next‑generation decisioning capabilities.

Roles :

• Build and deploy Gen AI applications using LLMs, embeddings, vector databases, and retrieval‑augmented generation (RAG).
• Create Python pipelines for model fine‑tuning, evaluation, inference, and data processing.
• Use LangChain and LangGraph to orchestrate multi‑step AI workflows, agentic systems, and complex reasoning pipelines.
• Implement secure API gateways, model governance, monitoring, and performance optimisation for production AI workloads.
• Partner with Data, Cloud, Product, and Engineering teams to deliver scalable, compliant, and high‑impact AI solutions.
• Evaluate emerging AI technologies and contribute to architectural decisions for enterprise AI platforms.

Requirements :

• Proficiency in Python for AI/ML engineering, model orchestration, and data workflows.
• Solid experience building and consuming RESTful APIs, including authentication, versioning, and performance tuning.
• Practical experience with LangChain for LLM orchestration and tool‑calling.
• Familiarity with LangGraph for building agentic workflows, stateful graph‑based reasoning, and multi‑step automation.
• Understanding of vector databases (FAISS, Milvus, Pinecone) and RAG architectures.