What you'll do
- Design and implement LLM-powered applications including RAG pipelines and agentic workflows
- Integrate open-source and proprietary models (OpenAI, Mistral, LLaMA, Gemini) into client products
- Build evaluation frameworks and monitor model performance in production
- Collaborate with clients to scope requirements and deliver iterative prototypes
- Write clean, well-documented Python code and maintain CI/CD pipelines
What we're looking for
- 2+ years of experience in AI/ML development
- Strong Python skills and hands-on experience with LangChain, LlamaIndex, or similar frameworks
- Familiarity with vector databases (Qdrant, Weaviate, Pinecone, ChromaDB)
- Understanding of prompt engineering, fine-tuning, and model evaluation
- Comfortable working async in a remote-first environment
Nice to have
- Experience with MLOps tools (MLflow, Weights & Biases, Ray)
- Contributions to open-source AI projects
- Exposure to multi-agent frameworks (AutoGen, CrewAI, LangGraph)
We’re looking for an AI Developer who can move fast, learn continuously, and ship production-ready AI systems. You’ll work directly with global clients — from AI startups to enterprise teams — building the AI stack that powers their products.