Alvyl Consulting
Website:
alvyl.com
Job details:
Experience · 3–5 years
Employment type · Full-time
Build and run LLM-powered applications that turn real business workflows into reliable AI agents. You’ll own the work from design and development through deployment and production monitoring.
Key Responsibilities
- Build stateful AI agents using LangChain and LangGraph, with tool calling, conditional routing, checkpointing, and human approvals.
- Develop RAG pipelines for document ingestion, chunking, embeddings, retrieval, and reranking.
- Build and test async FastAPI services with streaming responses and structured outputs.
- Set up LLM evaluations, tracing, and guardrails. Monitor latency, failures, and token costs in production.
- Deploy and maintain services using Docker, CI/CD, and cloud infrastructure.
Required Skills & Experience
- 3–5 years of professional software development experience, with strong production-level Python skills.
- 1–2 years of hands-on experience building and shipping LLM-powered applications to real users.
- Hands-on experience with LangChain and LangGraph, including stateful workflows, checkpointing, and tool calling.
- Strong FastAPI skills, including async programming, Pydantic, authentication, and streaming. Experience writing unit and integration tests with pytest.
- Practical experience with RAG, at least one vector database, and LLM provider APIs for tool calling and structured outputs.
- Working knowledge of Docker, Git, CI/CD, and at least one major cloud platform (AWS, Azure, or GCP).
Click on Apply to know more.