AI/ML Engineer

Job Summary

Seeking a Senior AI/ML Engineer to lead the development of a Python-based platform that ingests internal data sources (Hadoop, REST APIs) and applies locally deployed LLMs for text analytics, issue classification, and summarization. The ideal candidate combines strong engineering skills with hands-on LLM experience and the ability to collaborate across teams.

Key Responsibilities

Design & Development

• Architect and implement scalable Python-based data ingestion pipelines.
• Integrate with Hadoop and internal APIs for structured and unstructured data sourcing.
• Build modular components for data transformation, enrichment, and routing into downstream NLP systems.

LLM Integration

• Implement local LLM models for classification and summarization.
• Use prompt orchestration, chaining, and context-aware strategies to enhance NLP performance.
• Ensure reliability, scalability, and performance of LLM components in production.

Collaboration & Engineering Practices

• Work with data engineers, product owners, and ML researchers to refine use cases.
• Follow best practices (testing, CI/CD, documentation).
• Participate in design reviews and knowledge-sharing sessions.

Required Qualifications

• 4+ years of Python development experience.
• Strong background with big data technologies (Hadoop, PySpark, etc.).
• Hands-on experience with LLMs, embedding’s, vector databases, and RAG architectures.
• Experience with NLP tasks (classification, summarization, extraction).
• Background building/maintaining APIs and micro services.
• Experience with Model Context Protocol (MCP).
• Familiarity with LLMOps and scalable inference strategies.
• Prior work with Lang Chain, Hugging Face Transformers, or vLLM.
• Exposure to data science workflows, model evaluation, and feature engineering.
• Experience in financial services, enterprise, or regulated environments is a plus.