Technologies: Python, LLM APIs, Vector Databases

Our partner is looking for talented professionals ready to take the next step in their careers. This opportunity offers a collaborative environment filled with challenges, growth, and meaningful work.

As an AI Engineer (LLM Integration), you will work across multiple projects, collaborate with cross-functional teams, and deliver clear and transparent progress to clients. The ideal candidate is passionate about helping others, solving complex business problems, and tackling ambitious technical challenges.

Job Summary

Join an innovative AI-driven team where you'll design and build cutting-edge LLM-powered applications. Youll directly influence the future of intelligent systems by developing scalable solutions using modern AI tools, frameworks, and vector databases.

Responsibilities

- Design and implement end-to-end LLM applications using Python, FastAPI, and LangChain.

- Integrate and optimize models from OpenAI, Anthropic, Mistral, and other providers.

- Deploy scalable AI services on cloud platforms (AWS Lambda, GCP Vertex AI, Azure OpenAI).

- Build robust APIs and intelligent workflows alongside cross-functional teams.

- Utilize vector databases (Pinecone, FAISS, Weaviate) for semantic search and retrieval.

- Maintain clean, well-structured code using Git, Docker, and basic CI/CD.

- Actively participate in agile ceremonies and team meetings.

Requirements

- English proficiency B2+ (written and spoken).

- 5+ years of experience as an AI Engineer (LLM Integration).

- Excellent punctuality and accountability.

- Strong proficiency in Python, FastAPI, and LangChain.

- Hands-on experience with LLM APIs (OpenAI, Anthropic, Mistral).

- Experience deploying cloud applications (AWS, GCP, Azure).

- Solid understanding of vector databases (Pinecone, FAISS, Weaviate).

- Familiarity with Git, Docker, and basic CI/CD workflows.

Nice to Have

- Experience with LlamaIndex, Hugging Face, Redis, or Streamlit.

- Frontend integration skills (TypeScript / Next.js).

- Knowledge of Knowledge Graphs and semantic search concepts.

Position Details

- Type: Full-time contractor

- Hours: Up to 40 hrs/week

- Schedule: Flexible core hours

- Location: 100% remote (LATAM)