Senior AI Engineer (FDE Heavy)
New
J
JobgetherGenerative AI
Remote from anywhere in IndiaFull-TimeSenior
Salary7,000,000 - 10,000,000 INR per year
Apply NowOpens the employer's application page
Job Details
- Experience
- At least 5 years of overall software engineering experience, including significant recent experience in Applied AI, Generative AI, or LLM-based application development.
- Required Skills
- PythonGenerative AILangChain
Requirements
- At least 5 years of overall software engineering experience, including significant recent experience in Applied AI, Generative AI, or LLM-based application development.
- Expert-level proficiency in Python and the ability to write clean, modular, scalable, testable, production-quality code.
- Hands-on experience designing, building, and deploying production-grade LLM applications using LangChain, LangGraph, or equivalent frameworks.
- Experience developing multi-agent workflows involving orchestration, tool calling, state management, asynchronous execution, and long-running tasks.
- Strong understanding of RAG architectures, including document processing, chunking, embeddings, retrieval, reranking, and vector search optimisation.
- Experience building automated LLM evaluation pipelines for output quality, accuracy, hallucinations, task completion, and reliability.
- Ability to independently own complex technical challenges and deliver end-to-end AI solutions.
- Strong understanding of production-grade AI architecture, enterprise integrations, workflow automation, and scalable system design.
- Ability to collaborate with stakeholders and translate business needs into technical implementations.
- Strong problem-solving abilities and ability to balance technical quality with practical business outcomes.
Responsibilities
- Architect, develop, and deploy multi-agent systems using LangGraph, LangChain, or equivalent orchestration frameworks.
- Own the AI development lifecycle, including architecture, prompt engineering, tool integration, deployment, monitoring, evaluation, and optimisation.
- Translate complex business requirements into agent behaviours, tool specifications, execution strategies, and reliable workflows.
- Work with customers, product teams, and engineering stakeholders to deliver production-ready AI applications.
- Design and optimise RAG pipelines, including document processing, chunking, embeddings, retrieval, reranking, and vector search.
- Develop automated LLM evaluation frameworks to measure accuracy, hallucinations, task completion, and reliability.
- Integrate AI agents with enterprise applications, databases, APIs, and existing technology infrastructure.
- Optimise model inference costs, response latency, and system performance.
- Establish LLMOps practices for tracing, monitoring, debugging, version control, deployment, and production evaluation.
- Troubleshoot technical challenges and performance bottlenecks, and improve systems using real-world usage and evaluation results.
View Full Description & ApplyYou'll be redirected to the employer's site