GenAI Solutions Engineer — Production-Ready LLM Apps

iSystems Ltd; Islamabad; On-site; PKR 1,500,000 - 3,000,000; Full time

Job summary

iSystems Ltd is seeking an experienced software engineer to build generative AI applications with LLM-powered features, RAG pipelines, and enterprise search capabilities. You will fine-tune models, implement prompt management, and integrate OpenAI, Anthropic, Azure OpenAI, and open-source endpoints within secure, scalable production environments.

You will also optimize latency, cost, and evaluation metrics, working directly with client engineers and data scientists to translate business

Qualifications

• Proficient Python development with GenAI/LLM apps.
• Experience with LangChain or similar orchestration frameworks.
• Knowledge of vector DBs and embedding strategies; graph DB tooling is a plus.
• Understanding LLM failure modes and mitigations.
• Experience with model fine-tuning (LoRA/QLoRA).
• Hands-on with enterprise GenAI/agentic platforms (Azure/AWS/Vertex AI) and open-source frameworks.

Responsibilities

• Build GenAI applications — LLM-powered features and copilot experiences.
• Design and implement RAG pipelines and embedding selection.
• Tune and adapt models when prompts/RAG are insufficient.
• Engineer production prompts and manage prompt context.
• Integrate LLM APIs with auth, rate limits, and cost controls.
• Instrument apps for evaluation with logging and feedback loops.
• Optimize latency and token cost via caching and routing.
• Translate client requirements into concrete GenAI features.
• Communicate tradeoffs to non-technical stakeholders.
• Collaborate with architects, data scientists, and QA.

Skills

Python

LangChain

LlamaIndex

Vector databases

Neo4j

LLM failure handling

LoRA/QLoRA

APIs & auth

Prompt engineering

LLMOps tooling

Tools

LangSmith

Weights & Biases

Job description

iSystems Ltd is seeking an experienced software engineer to build generative AI applications with LLM-powered features, RAG pipelines, and enterprise search capabilities. You will fine-tune models, implement prompt management, and integrate OpenAI, Anthropic, Azure OpenAI, and open-source endpoints within secure, scalable production environments.

You will also optimize latency, cost, and evaluation metrics, working directly with client engineers and data scientists to translate business