Forward-Deployed GenAI Engineer — LLM Apps & RAG

iSystems Ltd; Karachi Division; On-site; PKR 2,000,000 - 4,000,000; Full time

Job summary

iSystems Ltd builds generative AI applications — LLM-powered features, RAG pipelines, and enterprise search that ship to production, not just a demo. You will design and implement robust GenAI systems, fine-tune models, and integrate multiple cloud and open-source platforms.

You will work withArchitects and Data Scientists to translate client requirements into concrete feature specs, while documenting decisions for maintainability and handoff.

Qualifications

• 4–8 yrs software engineering, with 1–3 yrs GenAI/LLM app building.
• Strong Python; experience with LangChain, LlamaIndex, or equivalent.
• Vector DBs and embedding strategies (Pinecone, Weaviate, pgvector).
• Understands LLM failure modes and mitigations.
• Model fine-tuning (LoRA/QLoRA) and evaluation harnesses.
• Experience with enterprise GenAI platforms (Azure AI Foundry, AWS Bedrock, Vertex AI) and open-source frameworks.
• API design and integration with auth, rate limiting, streaming.
• Prompt-versioning and LLMOps tooling (LangSmith, Weights & Biases).
• Clear architecture docs and ability to work with client engineers.

Responsibilities

• Build GenAI applications — LLM-powered features, copilot/chat experiences.
• Design and implement RAG pipelines: chunking, embedding, hybrid retrieval, re-ranking.
• Fine-tune and adapt models (LoRA/QLoRA) when needed.
• Engineer and version production prompts; integrate prompt management.
• Integrate LLM APIs and open-source model endpoints with auth and cost controls.
• Instrument apps for evaluation — output logging, quality scoring, human feedback loops.
• Optimize latency and token cost via caching, batching, and model routing.
• Translate client requirements into concrete GenAI feature specs.
• Document architecture and prompt design decisions for handoff and maintainability.
• Collaborate with architects and data scientists during embedded delivery.

Skills

Python programming

GenAI / LLM development

Collaborative work

Tools

Python

LangChain

LlamaIndex

Pinecone

Weaviate

pgvector

Neo4j

Azure AI Foundry

AWS Bedrock

Vertex AI

LangSmith

Weights & Biases

Job description

iSystems Ltd builds generative AI applications — LLM-powered features, RAG pipelines, and enterprise search that ship to production, not just a demo. You will design and implement robust GenAI systems, fine-tune models, and integrate multiple cloud and open-source platforms.

You will work withArchitects and Data Scientists to translate client requirements into concrete feature specs, while documenting decisions for maintainability and handoff.