AI/ML Engineer

AI/ML Engineer

1 year +

4 days onsite NYC

Job Summary

We are seeking a highly skilled Senior Developer to lead the development of a Python-based platform that ingests internal data sources (e.g., Hadoop, REST APIs) and applies locally deployed language models (LLMs) for text analysis, including issue classification and summarization. This role requires a blend of strong engineering expertise in building scalable data systems and good communication skills.

Key Responsibilities

Design & Development

• Architect and implement a robust data ingestion pipeline using Python.

• Integrate with Hadoop and/or internal APIs for sourcing structured and unstructured data.

• Design modular components for data transformation, enrichment, and routing to downstream NLP models.

LLM Integration

• Incorporate local LLM models for classification and summarization tasks.

• Use prompt orchestration, chaining, and context-aware techniques to improve NLP accuracy and consistency.

• Ensure performance and stability of LLM-based components in production environments.

Collaboration & Engineering Practices

• Work closely with data engineers, product owners, and ML researchers to refine use cases and deliver high-quality solutions.

• Follow modern software engineering best practices including testing, CI/CD, and code documentation.

• Participate in design reviews and knowledge-sharing sessions.

Required Qualifications

• 4+ years of professional experience in Python software development.

• Proven experience working with big data systems, particularly Hadoop, PySpark, or related technologies.

• Practical experience using LLMs, vector databases, embedding pipelines, and retrieval-augmented generation (RAG) architectures.

• Familiarity with NLP tasks such as classification, summarization, and information extraction.

• Experience building or maintaining APIs and microservices.

• Experience with Model Context Protocol (MCP) for managing prompts and contextual data across LLM applications.

Preferred Qualifications

• Familiarity with LLMOps tools and scalable inference strategies.

• Prior work with LangChain, Hugging Face Transformers, or vLLM runtime environments.

• Data scientist–related experience, such as collaborating on model training and evaluation, aligning data processing logic to ML objectives, or working on feature engineering and experimentation pipelines.

• Background in financial services, enterprise software, or regulated environments.