Senior AI / LLM Engineer

ThinkScoop Inc; Bengaluru; Hybrid; INR 1,500,000 - 2,500,000; Full time

Benefits offered by this job

Competitive salary with performance-linked bonuses

Remote-friendly with async-first culture

Access to latest LLM platforms and tooling budgets

Equity participation for exceptional contributors

Job summary

ThinkScoop Inc in Bengaluru is seeking a Senior AI/LLM Engineer to design and operate production AI systems. The role demands 4+ years of software engineering experience, including 2+ years in production ML or LLM systems. Responsibilities include implementing LLM pipelines, setting up infrastructure, and client collaboration. You’ll work in a senior, agile team that impacts architectural decisions and offers a competitive salary with performance-linked bonuses. Interested candidates should send their CV to [e-mail].

Qualifications

• 4+ years of software engineering experience with 2+ years in production ML or LLM systems.
• Strong skills in Python and experience with frameworks like LangChain, LlamaIndex.
• Experience building and evaluating RAG pipelines at production scale.

Responsibilities

• Design and implement production RAG systems, LLM pipelines, and multi-agent workflows.
• Build evaluation frameworks to measure accuracy, hallucination rate, and latency.
• Work directly with clients to translate business requirements into AI architectures.

Skills

Software engineering experience

Python

LangChain

Vector databases

Prompt engineering

Cloud infrastructure

Containerization

Tools

AWS

GCP

Azure

Docker

Kubernetes

Job description

About the role

We're looking for a Senior AI/LLM Engineer to design and operate intelligent systems in production. You'll work across the full lifecycle – from architecture and evaluation harnesses to deployment and monitoring. This isn't a research role. You'll be building AI systems that run real workflows for real clients, and you'll own the outcome.

What you’ll do

• Design and implement production RAG systems, LLM pipelines, and multi-agent workflows
• Build evaluation frameworks to measure accuracy, hallucination rate, and latency before every deployment
• Set up LLMOps infrastructure – logging, monitoring, cost tracking, and model versioning
• Work directly with clients to translate business requirements into AI architectures
• Conduct code reviews, define engineering standards, and mentor junior engineers
• Own end-to-end delivery from architecture to production handover

What we’re looking for

• 4+ years of software engineering experience with 2+ years in production ML or LLM systems
• Strong Python skills and experience with LangChain, LlamaIndex, or similar frameworks
• Hands‑on experience with vector databases (Pinecone, Weaviate, Qdrant, pgvector)
• Experience building and evaluating RAG pipelines at production scale
• Familiarity with OpenAI, Anthropic, Cohere, or open‑source LLM APIs
• Strong understanding of prompt engineering, context management, and retrieval strategies
• Experience with cloud infrastructure (AWS, GCP, or Azure) and containerisation (Docker, Kubernetes)

Nice to have

• Experience with multi-agent frameworks (AutoGen, CrewAI, LangGraph)
• Familiarity with LLMOps tools (Langfuse, Helicone, Phoenix, W&B Weave)
• Prior consulting or client-facing project delivery experience
• Contributions to open-source AI tooling

What we offer

• Work on real production AI systems used by enterprise clients – not internal demos
• Senior, small team with direct impact on architecture decisions
• Competitive salary with performance-linked bonuses
• Remote-friendly with async-first culture
• Access to the latest LLM platforms, APIs, and tooling budgets
• Equity participation for exceptional contributors

Think you're a good fit?

We read every email. Send your CV and two lines on why you want this role to [e-mail]