Location: Remote / Hybrid
Engagement: Full-time
About the Role
We’re looking for an Applied AI Engineer who is passionate about building real systems with modern AI tools. This is not a research role — you’ll be working hands-on with large language models (LLMs), APIs, and agentic frameworks to create usable, production-ready solutions.
The ideal candidate is someone who enjoys experimentation, can demonstrate projects they’ve built, and thrives in translating cutting-edge AI ideas into working applications.
Key Responsibilities
- Design, prototype, and deploy applications using LLMs and generative AI APIs (OpenAI, Anthropic, etc.).
- Implement Retrieval-Augmented Generation (RAG) pipelines with vector databases, search, and embeddings.
- Develop and extend agentic AI systems using frameworks such as OpenAI Agent SDK, LangChain, or CrewAI.
- Build integrations with third-party APIs and services (e.g., Slack, Gmail, internal systems).
- Work closely with product and engineering teams to take prototypes into scalable deployments.
- Document your work and demonstrate “working handiwork” — actual projects and code, not just theory.
What We’re Looking For
- 1–3 years of practical experience in software engineering, data engineering, or ML engineering.
- Strong coding skills in Python (bonus: Node.js, TypeScript).
- Hands-on experience with at least one agentic AI framework (e.g., OpenAI Agent SDK, LangChain, CrewAI).
- Familiarity with cloud platforms (AWS, GCP, or Azure).
- Comfort with databases, APIs, and building small end-to-end systems.
- Portfolio of projects, GitHub repos, or demos that showcase your ability to build things.
Nice to Have
- Exposure to MLOps concepts (deployment, monitoring, CI/CD).
- Understanding of prompt engineering and evaluation techniques.
- Experience with vector DBs (Pinecone, Weaviate, Milvus, FAISS).
- Curiosity to learn new frameworks and adapt quickly.