AI Engineer (Generative AI)

Merik Solutions; Islamabad; On-site; PKR 2,000,000 - 4,000,000; Full time

Job summary

Merik Solutions in Islamabad is seeking an experienced software engineer to join our engineering hub building generative AI products for enterprise clients across the US, Gulf, and Europe.

You will ship LLM-powered features end to end — from prompt design and retrieval pipelines to evaluation, guardrails, and production deployment.

This is a high‑ownership role on a fast‑growing team where your work goes straight into client products.

Qualifications

• 3+ years of software engineering experience.
• Strong Python skills.
• Hands-on experience shipping LLM features with OpenAI, Anthropic, or open-weight models.
• Familiarity with vector databases and embedding-based retrieval.
• Solid grasp of REST APIs, async processing, and cloud deployment.
• Clear written English for documentation and client communication.

Responsibilities

• Build and ship RAG systems, AI agents, and LLM-backed APIs for client applications.
• Design retrieval pipelines with vector databases, chunking strategies, and reranking.
• Set up evaluation harnesses to measure quality, latency, and cost of AI features.
• Implement safety guardrails, prompt-injection defenses, and observability for LLM apps.
• Collaborate with US-based teams across time zones on architecture and delivery.
• Stay on top of the model landscape and advise clients on the right fit for each use case.

Skills

Python

LLM features

REST APIs

Async processing

Cloud deployment

Tools

LangChain

OpenAI API

Anthropic API

Pinecone

FastAPI

Docker

AWS

PostgreSQL

Redis

Job description

Join our Islamabad engineering hub to build generative AI products for enterprise clients across the US, Gulf, and Europe.

You will ship LLM-powered features end to end — from prompt design and retrieval pipelines to evaluation, guardrails, and production deployment.

This is a high‑ownership role on a fast‑growing team where your work goes straight into client products.

What your days will look like

• Build and ship RAG systems, AI agents, and LLM-backed APIs for client applications.
• Design retrieval pipelines with vector databases, chunking strategies, and reranking.
• Set up evaluation harnesses to measure quality, latency, and cost of AI features.
• Implement safety guardrails, prompt‑injection defenses, and observability for LLM apps.
• Collaborate with US‑based teams across time zones on architecture and delivery.
• Stay on top of the model landscape and advise clients on the right fit for each use case.

You might be a great fit if you...

• 3+ years of software engineering experience with strong Python skills.
• Hands‑on experience shipping LLM features with OpenAI, Anthropic, or open‑weight models.
• Familiarity with vector databases and embedding‑based retrieval.
• Solid grasp of REST APIs, async processing, and cloud deployment.
• Clear written English for documentation and client communication.

Bonus points (but not required!)

• Experience fine‑tuning or self‑hosting open‑weight models.
• Contributions to open source AI tooling.
• Experience with agentic frameworks and tool‑calling patterns.

Tools you'll work with

Python LangChain OpenAI API Anthropic API Pinecone FastAPI Docker AWS PostgreSQL Redis

We respect your time and want this to feel like a real conversation, not an interrogation. Here’s what to expect:

Interview process

1. Let’s chat
   A relaxed 30‑minute call where we get to know each other. We’ll share what we’re building and hear about what excites you
2. A 60‑minute session to share stories about projects you’ve worked on. Ask our engineers anything — seriously, anything
3. Build something together
   We’ll tackle a real problem as a team. No gotchas, no trick questions — just a chance to see how we work together
4. Meet your future teammates
   Hang out with the folks you’d be working with day‑to‑day. See if we’re the right crew for you