Application Architecture: Design, build, and maintain backend services that power generative AI features and machine learning workflows.
LLM & API Integration: Connect commercial and open-source large language models (LLMs) into client-facing software applications via APIs and SDKs.
RAG Implementation: Build and scale Retrieval-Augmented Generation (RAG) pipelines, managing vector stores and embedding generation for high-accuracy data retrieval.
Performance Tuning: Optimize application response times, lower latency, and manage token usage or computational costs effectively.
Code Quality & Testing: Write modular, testable code, perform rigorous debugging, and collaborate with cross-functional product squads.
What We Are Looking For
Experience Background:
Fresh graduates with strong academic/project portfolios or professionals with 2 to 3 years of software engineering experience.
Technical Stack: Proficiency in Python, JavaScript, or another primary programming language, coupled with a solid grasp of RESTful APIs.
AI Ecosystem Familiarity: Basic-to-intermediate knowledge of AI frameworks (e.g., LangChain, LlamaIndex), vector databases, and ML deployment concepts.
Engineering Fundamentals: Familiarity with version control (Git), cloud platforms (AWS/GCP/Azure), and containerization (Docker).
Mindset: Robust logical reasoning, eagerness to solve complex integration challenges, and a self-driven attitude.