About this role
Thinkscoop is hiring a Senior AI / LLM Engineer to design, build and operate production AI systems for client workflows. This full-time role is listed as Mohali / Remote and spans architecture, evaluation, deployment, monitoring and production handover. It is an engineering delivery role rather than a research position.
Responsibilities
- Design and implement production RAG systems, LLM pipelines and multi-agent workflows.
- Build evaluation frameworks that measure accuracy, hallucination rate and latency before deployment. Establish LLMOps infrastructure for logging, monitoring, cost tracking and model versioning.
- Work directly with clients to turn business requirements into AI architectures. Own end-to-end delivery, conduct code reviews, define engineering standards and mentor junior engineers.
Required qualifications
- 4+ years of software engineering experience, including 2+ years working on production ML or LLM systems. The role overview lists 4–8 years of experience.
- Strong Python skills and experience with LangChain, LlamaIndex or similar frameworks; hands-on experience with vector databases such as Pinecone, Weaviate, Qdrant or pgvector.
- Experience building and evaluating RAG pipelines at production scale; familiarity with OpenAI, Anthropic, Cohere or open-source LLM APIs; and a strong understanding of prompt engineering, context management and retrieval strategies.
- Experience with AWS, GCP or Azure and containerisation using Docker or Kubernetes.
Preferred, not required: Experience with multi-agent frameworks such as AutoGen, CrewAI or LangGraph; LLMOps tools such as Langfuse, Helicone, Phoenix or W&B Weave; consulting or client-facing delivery; and contributions to open-source AI tooling.
The posting describes a remote-friendly, async-first culture, a learning budget, access to LLM platforms and tooling budgets, competitive salary with performance-linked bonuses, and possible equity participation for exceptional contributors. No salary amount is stated.