Applied AI Engineer

Build like a founder. Ship like Spartan.

Our customers are scaling fast and so are we. That’s why we’re looking for an Applied AI Engineer to join our world-class team.

At Spartan, we don’t act like contractors. We embed with startups backed by YC, Pear VC, BlingCap, a16z, Techstars, and more — partnering with founders and engineers from Stanford, MIT, Yale, Google, Amazon, Uber, and beyond. Together, we help launch MVPs in 30 days and scale systems that power billions of requests.

This isn’t “just another AI role.” It’s a chance to work shoulder-to-shoulder with elite builders, solve complex startup challenges, and see your work directly drive companies raising millions on the global stage. You’ll also be at the frontier of AI: 70% of our portfolio is LLM-powered.

Key Responsibilities 

• Prompts & Interfaces: Design clear prompt templates and role scaffolds (System/User/Assistant). Prefer structured outputs (JSON/schema).
• Context & Memory: Keep chats relevant with windowing/summarization and retrieval-backed long-term memory; basic tenant/privacy scoping.
• RAG Pipeline: Chunk/clean docs, embed into a vector store, run hybrid retrieval (BM25 + dense), and return answers with citations.
• Grounded Answers: Favor evidence, cite sources, and abstain when unsure.
• Agent Loops & Tool Use: Implement Plan → Act → Observe → Iterate; call APIs/DBs via typed tool contracts.

Requirements

• Fluent in English — you’ll talk directly with US startup founders.
• 1+ years building production features (AI, search, or backend). We’re language-agnostic.
• Solid grasp of LLM fundamentals: chat vs completion, roles, tokens/context, structured prompts.
• Hands-on with vector retrieval concepts (BM25, embeddings, HNSW/IVF) and basic grounding (citations/abstention).
• Comfortable integrating external/internal tools via function-calling or typed contracts.
• Strong CS fundamentals and a builder’s mindset — you own problems end-to-end.

Nice to have: multi-agent patterns, safety/PII pipelines, streaming UX (SSE/WebSocket), multimodal.

Tech We Use 

LLM & tooling: OpenAI, Anthropic, Google, Mistral, Llama • LangChain / LangChain4j, LlamaIndex
Vector & search: Postgres/pgvector • Pinecone • Weaviate • Qdrant • Redis • Elasticsearch/BM25
Data & messaging: Postgres • MongoDB • DynamoDB • Redis • Kafka • Pulsar • SQS
Infra & ops: AWS • GCP • Azure • Kubernetes (k8s) • Terraform
CI/CD & observability: GitHub Actions • Jenkins • DataDog • Prometheus • Grafana • ELK

Perks & Benefits

💰 Competitive salary
🏝 Unlimited PTO + public holidays
🩺 Premium healthcare insurance
🏃 Sports coverage (Strava integration)
🏠 Hybrid working style
✈️ Annual company trip + monthly team parties

Career Growth

• Work with founders from Stanford, MIT, Yale, Google, Amazon, Uber, and more.
• Exposure to cutting-edge tech (LLMs, AI agents, cloud infra, real-time systems).
• Transparent growth path and mentorship from engineers who’ve taken 3 companies to IPO.
• Solve real startup challenges — every project feels like its own mini-startup.

Why Spartan

• 50+ MVPs launched, 3 IPOs, $100M+ raised.
• 95% engineer retention — because we hire the top 1%.
• You’ll never just “take tickets” here. You’ll own problems, ship fast, and grow with the founders we partner with.