AI Engineer

MacroCoderz; Pakistan; Remote; PKR 24,896,000 - 35,961,000; Full time

Job summary

MacroCoderz is hiring a remote AI Engineer to build production LLM applications for clients worldwide. You will design the approach, write code, measure quality with evaluation sets, and ship to production.

Most projects use Python or TypeScript, models from OpenAI, Anthropic and open-source providers, and a vector database. You will design and implement LLM-powered features, select models and architectures, create evaluation sets, and integrate AI capabilities with client systems while

Qualifications

• 2+ years of professional software engineering experience.
• At least one LLM application shipped to real users.
• Strong Python or TypeScript proficiency.
• Hands-on experience with LLM APIs, embeddings and prompt design.

Responsibilities

• Design and build LLM-powered features from prompt and retrieval design to API and deployment.
• Choose models and architectures, justify trade-offs in cost, latency and quality.
• Build evaluation sets and measure changes before shipping.
• Integrate AI features with client systems (CRMs, databases, internal APIs, SaaS tools).
• Monitor production behaviour and fix failures, hallucinations and regressions.

Skills

Python

TypeScript

LLM APIs

Embeddings

Prompt design

Retrieval augmented generation

English writing

Job description

MacroCoderz is hiring a remote AI Engineer to build production LLM applications - AI agents, RAG systems and integrations - for clients worldwide.

As an AI Engineer at MacroCoderz you build the generative AI features our clients put in front of real users: assistants that answer from a company's own documents, agents that take actions in business systems, and LLM features added to existing products.

The work is end to end. You design the approach, write the code, measure quality with evaluation sets, and ship to production. Most projects use Python or TypeScript, models from OpenAI, Anthropic and open-source providers, and a vector database.

What you will do

• Design and build LLM-powered features, from prompt and retrieval design to API and deployment.
• Choose models and architectures for each problem, and justify the trade-offs in cost, latency and quality.
• Build evaluation sets and use them to measure every change before it ships.
• Integrate AI features with client systems: CRMs, databases, internal APIs and SaaS tools.
• Monitor production behaviour and fix failures, hallucinations and regressions.

What we are looking for

• 2+ years of professional software engineering, with at least one LLM application shipped to real users.
• Strong Python or TypeScript.
• Hands-on experience with LLM APIs, embeddings and prompt design.
• Understands how retrieval-augmented generation works and where it fails.
• Clear written English: most of our coordination happens in writing.

Nice to have

• Experience with LangChain, LlamaIndex or a similar framework - and knowing when not to use one.
• Fine-tuning or running open-source models.
• Client-facing or consulting experience.

Location

fully remote, open to applicants worldwide.