About the role
As an AI Engineer at TheWebVale, you will integrate language models, computer vision APIs, and intelligent automations into client platforms. You will build practical solutions such as document parsers, clinic triage assistants, and customer support bots for diverse businesses.
You will collaborate with full-stack developers and our founder during focused two-to-three week release cycles. You will design reliable prompt pipelines, implement structured schema outputs, and ensure clients maintain complete control over their model interactions.
What you will do
- Integrate commercial and open-source language models into web and mobile backends.
- Design prompt templates with strict validation rules for structured JSON responses.
- Build retrieval-augmented generation pipelines using vector embeddings and similarity search.
- Implement caching layers to reduce model API consumption and improve response latency.
- Write automated evaluation scripts to detect model hallucination and response drift.
- Collaborate with frontend developers to stream model outputs smoothly into user interfaces.
What you will need
- Hold 2–4 years of software development experience with focused work in AI or ML.
- Demonstrate strong proficiency in Python or TypeScript with async API integration.
- Show practical experience connecting language model APIs from OpenAI, Anthropic, or Google.
- Understand vector embeddings, similarity search algorithms, and chunking strategies.
- Maintain disciplined Git version control workflows and clear documentation.
- Communicate AI capabilities and technical limitations honestly to non-technical clients.
Nice to have
- Familiarity with vector databases such as Pinecone, Qdrant, or Chroma.
- Experience with LangChain, LlamaIndex, or LiteLLM routing libraries.
- Knowledge of local model inference runtimes like Ollama or vLLM.