Production GenAI Engineer - LLM Apps & RAG Pipelines

Systems Limited; Islamabad; On-site; PKR 1,500,000 - 2,400,000; Full time

Job summary

Systems Limited is seeking a skilled software engineer to build GenAI applications, including LLM-powered features, RAG pipelines, and enterprise search. You will design and implement end-to-end solutions, optimize latency, and collaborate with architects and data scientists to deliver production-ready capabilities.

The role requires strong Python, experience with LangChain and vector databases, and familiarity with model fine-tuning (LoRA/QLoRA).

Qualifications

• 4–8 yrs software engineering, with 1–3 yrs GenAI/LLM app building.
• Strong Python; experience with LangChain, LlamaIndex, or equivalent.
• Vector databases and embedding strategies; graph tooling experience helpful.
• Understands LLM failure modes and mitigations.
• Model fine-tuning techniques (LoRA/QLoRA) and evaluation harnesses.
• Experience with enterprise GenAI platforms and API design; LLMOps tooling experience.

Responsibilities

• Build GenAI applications - LLM-powered features and RAG pipelines.
• Design and implement RAG pipelines; embedding selection and retrieval.
• Fine-tune and adapt models (LoRA/QLoRA) when needed.
• Engineer and version production prompts; document architecture decisions.
• Integrate LLM APIs and open-source endpoints with auth and rate limits.
• Instrument apps for evaluation: logging, quality scoring, feedback.
• Optimize latency and token cost via caching and model routing.
• Communicate tradeoffs to non-technical stakeholders.
• Collaborate with architects, data scientists, and QA; embed delivery with clients.

Skills

Python

LangChain

LlamaIndex

Vector databases

Pinecone

Weaviate

Neo4j

LLM failure modes

LoRA/QLoRA

LLMOps

API design

Prompt-versioning

Tools

LangChain

LlamaIndex

OpenAI API

Azure OpenAI

Weaviate

Pinecone

Neo4j

Job description

Systems Limited is seeking a skilled software engineer to build GenAI applications, including LLM-powered features, RAG pipelines, and enterprise search. You will design and implement end-to-end solutions, optimize latency, and collaborate with architects and data scientists to deliver production-ready capabilities.

The role requires strong Python, experience with LangChain and vector databases, and familiarity with model fine-tuning (LoRA/QLoRA).