LLM / RAG Expert

Senior AI Engineer (LLM / RAG)

About Us

We are an AI startup building production-grade intelligent systems that help organizations automate complex workflows, extract insight from unstructured data, and deploy reliable AI agents at scale. Our platform combines modern LLM architectures, retrieval systems, and applied machine learning to deliver measurable business outcomes.

We are looking for an experienced engineer with deep expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and scalable AI infrastructure to help shape our core product and technical direction.

Role Overview

As a Senior AI Engineer focused on LLMs and RAG systems, you will design, build, and optimize AI applications that leverage state-of-the-art language models, vector search, agent frameworks, and enterprise data pipelines.

You will work closely with product, engineering, and leadership teams to develop scalable AI systems that are production-ready, secure, and performant.

This is a hands-on engineering role for someone who enjoys solving difficult applied AI problems and shipping real-world systems.

Key Responsibilities

• Design and implement scalable LLM-powered applications and AI services
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines
• Develop semantic search and vector database architectures
• Fine-tune and evaluate open-source and commercial language models
• Implement prompt engineering, agent orchestration, and tool-calling workflows
• Build data ingestion and embedding pipelines for structured and unstructured data
• Improve model reliability, latency, hallucination reduction, and evaluation frameworks
• Collaborate with product and design teams to deliver AI-native user experiences
• Deploy and monitor AI systems in cloud-native production environments
• Establish best practices around AI governance, observability, and security

Required Skills & Experience

• 4+ years of software engineering experience
• 2+ years working directly with LLMs, generative AI, or NLP systems
• Strong Python engineering skills
• Experience building production RAG systems
• Experience with vector databases such as:
  • Pinecone
  • Weaviate
  • Qdrant
  • Chroma
  • FAISS
• Experience with frameworks such as:
  • LangChain
  • LlamaIndex
  • Haystack
  • DSPy
• Strong understanding of:
  • Embeddings
  • Chunking strategies
  • Re-ranking
  • Retrieval optimization
  • Prompt engineering
  • AI evaluation techniques
• Experience integrating APIs from providers such as:
  • OpenAI
  • Anthropic
  • Cohere
  • Google Gemini
• Familiarity with cloud infrastructure:
  • AWS
  • GCP
  • Azure
• Experience with Docker, Kubernetes, CI/CD, and scalable backend systems
• Strong understanding of software architecture and production engineering principles

Nice to Have

• Experience fine-tuning open-source models (Llama, Mistral, DeepSeek, Mixtral)
• Experience with AI agents and multi-agent orchestration
• Knowledge of graph RAG and knowledge graph systems
• Experience with multimodal AI systems
• Familiarity with evaluation frameworks and LLM observability tools
• Experience in startup or high-growth environments
• Contributions to open-source AI projects or published technical content

What Success Looks Like

• You ship reliable AI features quickly and iteratively
• You improve retrieval quality and model performance measurably
• You help define scalable AI architecture standards
• You balance experimentation with production discipline
• You contribute strategically to product direction and technical innovation

Tech Stack

Examples of technologies we currently use or are exploring:

• Python
• FastAPI
• LangChain / LlamaIndex
• OpenAI / Anthropic APIs
• PostgreSQL
• Vector Databases
• Docker & Kubernetes
• AWS / GCP
• Redis
• Airflow
• Elasticsearch

Why Join Us

• Opportunity to build cutting-edge AI products from the ground up
• High ownership and technical influence
• Fast-moving startup environment
• Direct exposure to product and company strategy
• Competitive salary + equity
• Flexible working arrangements