Remote job
AI Engineer
Job details
About this role
Role overview Build and operate AI features that address practical business needs, taking them from design into dependable production software. The work spans language-model applications, retrieval over business information, and the engineering practices needed to assess quality, protect users, and keep systems reliable as usage grows.
Responsibilities - Design and deliver language-model features integrated with production applications. - Create retrieval systems for documents, catalogues, and other business data. - Develop evaluation pipelines, regression checks, and measures of relevance and groundedness. - Add safeguards, output validation, monitoring, and operational tracing to deployed AI systems. - Manage model selection, inference cost, and response time as demand changes. - Work with product and customer stakeholders to set achievable requirements and document responsible, secure practices.
Requirements - 4–8 years of software engineering experience, including at least two years delivering AI or LLM features in production. - Strong production Python skills, including asynchronous programming, and solid experience with APIs, databases, testing, and deployment. - Familiarity with LLM APIs, structured outputs, streaming, and managing cost and latency. - Hands-on production RAG experience, including embeddings, chunking, vector stores, reranking, and retrieval diagnostics. - Experience with tool calling or multi-step agent workflows, AI evaluation, prompt-injection defenses, output validation, and monitoring. - Professional spoken and written English; applicants must be Indian nationals authorized to work in India without sponsorship.
Nice to have Experience with PyTorch and LoRA/QLoRA, MLflow or Weights & Biases, OpenTelemetry, EU AI Act transparency considerations, or manufacturing, engineering, and operations data.
Benefits and work setup Regular full-time role based in India, with hybrid or remote work options and no expected travel.