AI / LLM & Cloud Systems Engineer

The Mission

Role Overview

Join our core AI research squad engineering enterprise-grade intelligence layers. You will build end-to-end Retrieval-Augmented Generation (RAG) pipelines, semantic vector search indexes, and automate complex knowledge-worker workflows using modern foundation models and edge infrastructure.

What You'll Do

Key Responsibilities

• Develop scalable RAG pipelines using LangChain/LlamaIndex, pgvector, and hybrid BM25 semantic retrieval.
• Fine-tune open-source models (Llama 3, Mistral) for domain-specific tasks and evaluate inference latencies.
• Build low-latency streaming endpoints with Python FastAPI and edge gateways.
• Architect cloud infrastructure on AWS/GCP with Terraform and automated observability (Prometheus/Grafana).
• Implement strict guardrails, prompt security checks, and token optimization layers.

What We Look For

Required Qualifications

• 2-4 years of experience in backend/cloud software engineering with a strong focus on Python and AI systems.
• Hands-on experience with vector databases (Pinecone, pgvector, Qdrant) and embedding models.
• Solid understanding of LLM prompt engineering, embeddings, context windows, and hallucination reduction.
• Experience deploying containerized workloads using Docker, Kubernetes, or AWS ECS/Lambda.

Bonus Points

Nice to Have

• Experience fine-tuning models with LoRA/QLoRA on cloud GPUs.
• Familiarity with distributed caching, Redis, and event-driven architectures.