Forward Deployed Engineer GenAI📣 إعلان

About the Role

Systems Limited is seeking a Forward Deployed Engineer GenAI to join their team in Saudi Arabia. This full-time role involves building and deploying generative AI applications, focusing on LLM-powered features, RAG pipelines, and enterprise search solutions that are production-ready. The position requires 5-10 years of experience, with a specific focus on hands-on GenAI/LLM application development.

Key Responsibilities

• Build GenAI applications, including LLM-powered features, copilot/chat experiences, and enterprise search.
• Design and implement RAG pipelines, covering chunking strategy, embedding selection, hybrid retrieval, re-ranking, and GraphRAG where structured retrieval is necessary.
• Fine-tune and adapt models using techniques like LoRA/QLoRA when prompt engineering and RAG are insufficient.
• Engineer and version production prompts, integrating prompt/context management into the application layer.
• Integrate LLM APIs (OpenAI, Anthropic, Azure OpenAI) and open-source model endpoints with authentication, rate-limiting, and cost controls.
• Instrument applications for evaluation, including output logging, quality scoring, and 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 Agentic AI Architects and Data Scientists on shared components.
• Document architecture and prompt design decisions for handoff and maintainability.

Required Qualifications and Experience

• 4–8 years of experience in software engineering, with 1–3 years specifically in hands-on GenAI/LLM application building.
• Strong proficiency in Python and experience with orchestration frameworks such as LangChain, LlamaIndex, or equivalents.
• Experience with vector databases and embedding strategies (*, Pinecone, Weaviate, pgvector), along with knowledge-graph/graph-database tooling (*, Neo4j) where applicable.
• Understanding of LLM failure modes (hallucination, context-window limits, cost blowup) and the ability to design mitigations.
• Experience with model fine-tuning techniques (LoRA/QLoRA) and evaluation harnesses.
• Hands-on experience with enterprise GenAI/agentic platforms such as Microsoft Azure AI Foundry, AWS Bedrock (including Strands Agents SDK), and Google Vertex AI. Familiarity with open-source frameworks (LangChain, LlamaIndex) is beneficial where no platform is mandated.
• API design and integration experience, including authentication, rate limiting, and streaming responses.
• Familiarity with prompt-versioning and LLMOps tooling (*, LangSmith, Weights & Biases, or similar).

Key Skills

• Clear technical writing skills, capable of documenting RAG architecture for non-technical stakeholders.
• Comfortable working directly with client engineers during embedded delivery.
• Collaborative approach, working effectively with architects, data scientists, and QA without requiring extensive pre-specification.
• Adaptability under ambiguity, recognizing that prompt-based systems necessitate rapid iteration and tolerance for imperfect initial attempts.

Work Environment

The role involves working in a collaborative environment, engaging with various technical and non-technical stakeholders, including client engineers, architects, data scientists, and QA teams. The nature of GenAI development requires a proactive and adaptable approach to problem-solving and iteration.

Application Process

Candidates who meet the specified requirements are encouraged to apply for this full-time position. Salary details will be discussed during the interview process.