This role is for one of Weekday’s clients
Salary range: Rs 7000000 – Rs 10000000 (ie INR 70 – 100 LPA)
Min Experience: 5+ years
Location: Remote (India)
JobType: full-time
We are looking for a highly skilled Senior AI Engineer with strong expertise in Applied AI, Generative AI, and production-grade agentic systems. The ideal candidate will be responsible for architecting, building, deploying, and scaling sophisticated AI agents and Retrieval-Augmented Generation (RAG) pipelines for complex enterprise workflows.
This is a hands-on, engineering-intensive role requiring strong end-to-end ownership, from translating ambiguous business requirements into functional AI solutions to integrating, deploying, and optimising reliable systems in production. The role places particular emphasis on Forward Deployed Engineering (FDE), requiring close collaboration with product, engineering, and business teams to solve real-world enterprise problems through practical AI implementations.
Requirements
Key Responsibilities
- Architect, develop, and deploy complex multi-agent systems using LangGraph, LangChain, or equivalent frameworks to automate enterprise workflows and execute long-running, asynchronous tasks.
- Take end-to-end ownership of AI agent development, including system architecture, prompt engineering, tool integration, deployment, monitoring, evaluation, and continuous optimisation.
- Translate complex and ambiguous enterprise requirements into concrete AI-driven solutions, agent behaviours, tool definitions, execution plans, and reliable workflows.
- Work closely with customers, product teams, and engineering stakeholders to understand operational challenges and deliver production-ready AI applications.
- Design, build, and optimise RAG pipelines by improving document chunking, embedding generation, retrieval strategies, reranking, and vector search performance.
- Develop automated evaluation frameworks to measure agent accuracy, hallucination rates, task completion, and overall system reliability.
- Integrate AI agents with enterprise applications, databases, APIs, and existing technology infrastructure to enable intelligent automation and end-to-end task execution.
- Optimise model inference costs, response latency, and system performance through appropriate model selection and efficient orchestration strategies.
- Establish and implement LLMOps best practices covering tracing, monitoring, debugging, version control, deployment, and production evaluation.
- Troubleshoot complex technical challenges, identify performance bottlenecks, and continuously improve AI systems based on real-world usage and evaluation results.
Required Qualifications and Experience
- 5+ years of overall software engineering experience, with significant recent experience in Applied AI, Generative AI, or Large Language Model (LLM)-based applications.
- Expert-level proficiency in Python, with the ability to write clean, modular, scalable, testable, and production-quality code.
- Strong hands-on experience designing, building, and deploying production-grade LLM applications using LangChain, LangGraph, or equivalent orchestration frameworks.
- Proven experience developing complex agentic workflows involving multi-agent orchestration, tool calling, state management, asynchronous execution, and long-running tasks.
- Strong understanding of RAG architectures, including document processing, chunking strategies, embeddings, retrieval mechanisms, reranking, and vector search optimisation.
- Experience building automated LLM evaluation pipelines to assess output quality, accuracy, hallucinations, task completion rates, and system reliability.
- Ability to independently own technical problem-solving and deliver end-to-end AI solutions in dynamic enterprise environments.
- Strong collaboration and communication skills, with the ability to work directly with stakeholders and translate business requirements into technical implementations.
Must-Have Skills
- Python
- LangChain
- LangGraph
Key Focus Areas
- Production-grade AI agent architecture and development
- Forward Deployed Engineering (FDE) and enterprise AI implementation
- Multi-agent orchestration and agentic workflows
- Retrieval-Augmented Generation (RAG) pipeline development and optimisation
- LLM evaluation, monitoring, and LLMOps
- Enterprise system integrations and intelligent workflow automation
Source: Weekday AI job board (Workable (all companies)).
Report this job
Wrongly listed? Tell us why.