AI System Engineer

Overview

We are looking for an AI Systems Engineer to design, build, and optimize production-grade LLM systems. This role focuses on developing scalable AI solutions including agent workflows, Retrieval-Augmented Generation (RAG) pipelines, and fine-tuning processes. You will own prompt strategy, knowledge ingestion, evaluation, and continuous improvement of AI systems to ensure accuracy, reliability, and efficiency.

Key Responsibilities

• Design and optimize structured prompt frameworks and system prompts
• Build, deploy, and maintain AI agents for business workflows
• Architect and enhance RAG pipelines and knowledge retrieval systems
• Ingest, structure, and manage internal and external data sources
• Prepare and preprocess datasets for fine-tuning workflows
• Evaluate model outputs and continuously improve performance
• Implement guardrails, feedback loops, and monitoring systems
• Manage embeddings, chunking strategies, indexing, and retrieval logic
• Monitor hallucinations, prompt performance, and model drift
• Drive continuous improvements in AI system accuracy and scalability
• Identify and build AI-driven automation opportunities across business functions
• Collaborate with product, engineering, and stakeholders to enhance AI capabilities

Technical Skills

• Strong understanding of LLM behavior, strengths, and limitations
• Experience with prompt engineering, system prompts, and prompt chaining
• Hands-on experience with RAG architecture and vector databases
• Experience with embeddings, semantic search, and document indexing
• Proficiency in Python, API integrations, and building data pipelines
• Experience in dataset preparation, annotation, and fine-tuning workflows
• Familiarity with evaluation frameworks and prompt testing methodologies
• Understanding of performance optimization and cost efficiency in LLM systems

Data & Engineering

• Experience in data cleaning, normalization, and dataset curation
• Knowledge of knowledge ingestion pipelines and document parsing
• Familiarity with tools such as Pandas, SQL, and data pipeline frameworks

Analytical Skills

• Strong problem-solving and debugging capabilities for AI systems
• Ability to systematically evaluate and improve model performance
• Metrics-driven approach to decision-making

Organizational Skills

• Strong documentation and version control practices
• Ability to design reusable AI components and scalable workflows

Preferred Experience

• Experience with frameworks such as LangChain or LlamaIndex
• Familiarity with vector databases like Pinecone, Weaviate, or pgvector
• Experience with LLM providers such as OpenAI, Anthropic, Gemini, or HuggingFace
• Exposure to agent frameworks (LangGraph, CrewAI, AutoGen)
• Understanding of evaluation pipelines, hallucination detection, and prompt regression testing
• Experience with fine-tuning techniques such as LoRA or instruction tuning

What We’re Looking For

• Proactive and self-driven mindset
• Strong curiosity to explore and adopt new AI technologies
• Ability to identify gaps and build solutions independently
• Comfortable working with evolving tools and ambiguous problems
• Product-oriented thinking with a systems approach

Impact

This is a high-impact role where you will directly influence the accuracy, reliability, and scalability of AI systems used across the organization. You will play a key role in shaping how AI is integrated into business workflows and decision-making.

Ideal Candidate Profile

• 1–3 years of experience in applied AI/ML or LLM systems
• Experience building RAG-based applications or AI assistants
• Strong Python and data pipeline experience
• Hands-on experience with real-world AI system deployment
• Demonstrated initiative through projects or production systems