AI Engineer

Company Summary :

ELGO AI is a fast-growing startup redefining how enterprises build and deploy AI. We offer a powerful no-code enterprise-grade GenAI platform that enables organizations to create custom LLM-powered applications such as chatbots, smart document workflows, and automation agents 10x faster than traditional methods. Abstracting away the complexities of a production GenAI system, we aim to simplify enterprise AI adoption by making advanced GenAI capabilities accessible to non-technical teams. We are passionate about workflow orchestration, context-aware agents, full transparency and observability layer, scalable designs and enterprise-grade deployment, all grounded in responsible, secure, and user-centric design. Our vision is to become the go-to operating platform for practical AI solutions in Asia Pacific.

Job Description:

As an AI Engineer, you'll play a key role in the development and optimization of ELGO's no-code platform and LLM-based workflows. Instead of model training or fine-tuning, your focus will be on building reusable, configurable, and scalable LLM-powered components and highly optimized task agents that can be orchestrated by users without writing code. We also constantly push the frontiers on LLM techniques and designs to ensure that our agents are state-of-the-art.

You'll work closely with our CTO and engineering team to implement advanced LLM workflows, multi-agent logic, evaluation mechanisms, and performance monitoring that power real-world business applications.

The ideal person for the role would love the fast-changing and dynamic environment, working with new technologies and translating that into real world impact. He/she would also enjoy the opportunity to work on multiple real-world LLM systems, and constantly push him/herself to be better. He/she is would also be extremely proactive, both in working and learning.

Caution: this is likely going to be the toughest role ever you would have in your life, but it could also be the most rewarding.

Roles & Responsibilities:

• Develop and optimize backend systems for LLM workflow orchestration (retrieval, chaining, evaluation, memory, task-based agent optimizations).

• Implement reusable components (e.g., retrieval nodes, validation agents, evaluators) to power the no-code platform.

• Integrate and manage third-party models (e.g., OpenAI, Anthropic, AWS Bedrock, open-source models).

• Develop and maintain multi-agent and tool-augmented AI workflows for common enterprise use cases.

• Work on document processing, cross-system integrations, RAG pipelines, contextual memory management, and prompt engineering best practices.

• Research and development new techniques to tackle the toughest problems in LLM applications.

• Collaborate with front-end and platform engineers to support the no-code interface.

• Conduct systematic evaluations and performance tracking of LLM applications in production.

• Stay updated with emerging GenAI and agentic framework trends.

Requirements:

Core Requirements

• Bachelor's degree in Computer Science, AI/ML Engineering, or equivalent experience with about 2-4 years relevant working experience. Candidates without formal education but with strong practical experience are welcomed.

• Strong Python programming skills with experience in).

• Experience in building production-grade RAG applications and integrating with APIs.

• Familiarity with databases (e.g., PostgreSQL, MongoDB, Redis).

• Foundational programming knowledge (Git, Docker, OOP, FastAPI).

• Understanding of LLM architecture and practical applications.

Key Traits

• Strong problem-solving and systems thinking.

• Bias for action and comfort working in a fast-paced startup environment.

• Clear communication and collaborative mindset.

• Curiosity and openness to new ideas and technologies.

• Willingness to contribute beyond code – including product feedback, customer empathy, and roadmap planning.

Optional Requirements

• Familiarity with vector databases (e.g., Qdrant, Weaviate, Pinecone etc.).

• Experience building agentic workflows or using any frameworks like LangChain, Langgraph, CrewAI, AutoGen, Vercel SDK, OpenAI Agents SDK etc.

• Good understanding about transformers, LLMs, multi-agent systems, tool uses/function calling.

• Prior work with evaluation frameworks for LLM performance and safety.

What We Offer:

• A front-row seat to building the next generation of enterprise GenAI tooling and real-world applications.

• The opportunity to be part of a small but elite team of Asia's most promising GenAI startups.

• Exposure to real-world challenges and impactful deployments.

• A supportive and transparent team environment that values outcomes over hours. No politics, full focus on solving real problems.

• Growth opportunities across product, engineering, AI and R&D.

The Interview Process:

• There will be a total of 3 rounds of interview:

o 1st round: 30 minutes of general Q&A with the CEO

o 2nd round: 60 minutes technical session, where you will be given a real problem and is required to code out the solution within 30 minutes. Technical Q&A for the remaining time.

o 3rd round: 15 minutes for work arrangements and compensation package discussions.