Description

You will build and productionize LLM applications for summarization, classification, extraction, entity resolution, and recommendations.

This role is on-site.

Responsibilities

• Design agentic workflows, including tool-using agents, multi-step plans, guardrails, and audit mechanisms.
• Develop data intelligence pipelines: parsing, chunking, embedding, hybrid retrieval, and re-ranking.
• Create evaluation frameworks using golden datasets, regression tests, automated scoring, and human-review loops.
• Implement reliability patterns such as hallucination mitigation, grounding approaches, and prompt-injection defenses.
• Engineer GenAI systems adhering to enterprise constraints including security, governance, cost optimization, and observability.

Required Skills

• 10+ years of experience shipping production-grade services and APIs using Python.
• Hands-on experience with LLM application patterns, including RAG and tool calling.
• Experience building hybrid search and retrieval systems (vector + keyword) on large unstructured datasets.
• Strong fundamentals in software engineering, including CI/CD, logging, testing, and containerization.
• Ability to translate ambiguous business problems into clear technical designs and measurable outcomes.
• Proficiency with core skills: Python, LLM, RAG, APIs, CI/CD, Containerization.

Preferred Skills

• Experience with knowledge graphs, semantic search, or LLMOps practices.

Key Skills

Education

Any Graduate