Forward Deployed Engineer - GenAI

Systems Limited; Islamabad; On-site; PKR 1,800,000 - 3,000,000; Full time

Job summary

Systems Limited is building GenAI-powered applications, including copilot experiences and enterprise search, with robust RAG pipelines and embedding strategies. You will fine-tune models and implement production-grade prompts, while integrating multiple LLM APIs and ensuring scalable, cost-aware performance.

You will collaborate with architects, data scientists, and QA to translate client requirements into concrete GenAI features, document design decisions, and optimize latency and cost across

Qualifications

• 4–8 yrs software engineering with GenAI experience
• 1–3 yrs hands-on GenAI/LLM application building
• Strong Python and orchestration frameworks
• Experience with vector stores and embeddings
• Model fine-tuning (LoRA/QLoRA) experience
• Experience integrating OpenAI/Azure/AWS/Vertex endpoints
• Ability to explain tradeoffs to stakeholders
• Collaborative with architects, data scientists, QA

Responsibilities

• Build GenAI applications — LLM-powered features, copilot/chat experiences, enterprise search
• Design and implement RAG pipelines: chunking, embeddings, hybrid retrieval, re-ranking, GraphRAG
• Fine-tune/adapt models (LoRA/QLoRA) when prompt engineering fails
• Engineer/version production prompts; manage prompt/context in app layer
• Integrate LLM APIs with auth, rate limits, cost controls
• Instrument apps for evaluation — logging, quality scoring, feedback loops
• Optimize latency/cost via caching, batching, routing
• Translate client requirements into GenAI feature specs
• Communicate tradeoffs to non-technical stakeholders
• Collaborate with Agentic AI Architect and Data Scientists
• Document architecture and prompt design for handoff/maintainability

Skills

Python

LangChain

LlamaIndex

Vector databases

Neo4j

LoRA/QLoRA

LLM integration

API design

LLMOps tooling

Tools

LangChain

LlamaIndex

Pinecone

Weaviate

pgvector

Neo4j

Azure AI Foundry

AWS Bedrock

Google Vertex AI

Weights & Biases

LangSmith

Job description

Builds generative AI applications — LLM-powered features, RAG pipelines, and enterprise search that ship to production, not just a demo.

KEY RESPONSIBILITIES

• Build GenAI applications — LLM-powered features, copilot/chat experiences, enterprise search
• Design and implement RAG pipelines: chunking strategy, embedding selection, hybrid retrieval, re-ranking, GraphRAG where structured retrieval is needed
• Fine-tune and adapt models (LoRA/QLoRA) when prompt engineering and RAG aren't sufficient
• Engineer and version production prompts; build prompt/context management into the application layer
• Integrate LLM APIs (OpenAI, Anthropic, Azure OpenAI) and open-source model endpoints with auth, rate-limiting, and cost controls
• Instrument applications for evaluation — output logging, quality scoring, human-feedback loops
• Optimize latency and token cost through caching, batching, and model routing strategies
• Translate client business requirements into concrete GenAI feature specifications
• Communicate technical tradeoffs (cost, latency, accuracy) to non-technical product stakeholders
• Collaborate with the Agentic AI Architect and Data Scientists on shared components
• Document architecture and prompt design decisions for handoff and maintainability

REQUIREMENTS & SKILLS

• 4–8 yrs software engineering, with 1–3 yrs hands-on GenAI/LLM application building
• Strong Python; experience with LangChain, LlamaIndex, or equivalent orchestration frameworks
• Vector databases and embedding strategies (Pinecone, Weaviate, pgvector), plus knowledge-graph/graph-database tooling (Neo4j) where relevant
• Understands LLM failure modes (hallucination, context-window limits, cost blowup) and designs mitigations
• Experience with model fine-tuning techniques (LoRA/QLoRA) and evaluation harnesses
• Hands-on with enterprise GenAI/agentic platforms — Microsoft Azure AI Foundry, AWS Bedrock (incl. Strands Agents SDK), and Google Vertex AI; open-source frameworks (LangChain, LlamaIndex) a good-to-have where no platform is mandated
• API design and integration experience, including auth, rate limiting, and streaming responses
• Familiarity with prompt-versioning and LLMOps tooling (LangSmith, Weights & Biases, or similar)
• Clear technical writing — documents a RAG architecture for a non-technical stakeholder
• Comfortable working directly with client engineers during embedded delivery
• Collaborative — works with architects, data scientists, and QA without needing everything pre-specified