Staff Engineer (AI and LLM)

Job Title:            Staff Engineer – AI and LLM
Job Type:            Full-Time
Experience:        8–15+ Years

Mandatory Requirement:

·       Candidates must have a proven track record of building, deploying, and supporting LLM-powered applications in production environments. Experience limited to experimentation, proof-of-concepts, or prompt engineering alone will not be considered.

About the Role

·       We are seeking an experienced Staff Engineer to join a high-performing engineering team building AI-native products. This is a hands-on engineering role focused on designing, developing, and deploying production-grade LLM-powered applications. You will work closely with product, engineering, and leadership to build scalable AI systems that solve real-world business problems.

·       This role is ideal for someone who has successfully shipped LLM-based applications to production and has deep expertise in modern AI architectures, agentic workflows, and distributed systems.

Responsibilities

·       Design, develop, and deploy production-ready LLM-powered applications.

·       Build scalable AI services using modern LLM frameworks and orchestration tools.

·       Develop autonomous AI agents, RAG pipelines, and intelligent workflow automation.

·       Implement prompt engineering, evaluation frameworks, guardrails, caching, and monitoring.

·       Optimize inference performance, latency, reliability, and cost.

·       Collaborate with cross-functional teams to translate business requirements into AI-powered solutions.

·       Mentor engineers and establish engineering best practices for AI application development.

·       Drive architecture decisions and contribute to the technical roadmap.

Required Qualifications

·       8+ years of software engineering experience with strong backend development expertise.

·       Hands-on experience building and shipping LLM-based applications to production is mandatory.

·       Strong experience with Python and modern backend frameworks.

·       Experience integrating commercial and open-source LLMs (OpenAI, Anthropic, Gemini, Llama, Mistral, etc.).

·       Experience with AI orchestration frameworks such as LangGraph, LangChain, LlamaIndex, CrewAI, or similar.

Excellent problem-solving and communication skill.