AI/ML Engineer

Role Overview

AI/NLP Engineer (Individual Contributor) on the Data Science team. You will build production-grade AI solutions using Large Language Models (LLMs) and advanced retrieval/agent techniques to support real-time decision-making for public safety and intelligence workflows.

Responsibilities

• Design, build, and optimize AI-powered solutions using LLMs, RAG pipelines, semantic search, GraphRAG, and Agentic AI architectures
• Implement and experiment with large-scale language modeling advancements, including:
  • Prompt engineering
  • Model fine-tuning
  • Evaluation and monitoring
• Collaborate with product, backend, and data engineering to translate real-world problems into scalable, high-impact features
• Build and improve data ingestion and retrieval pipelines for real-time and batch AI applications
• Integrate external data sources (e.g., knowledge graphs, internal DBs, third-party APIs) to increase context awareness
• Apply best practices for prompt design, model alignment, and responsible AI safety/guardrails
• Stay current with emerging AI research; contribute via knowledge sharing, tech talks, and proof-of-concepts
• Write clean, well-documented, testable code; participate in peer reviews and design discussions
• Identify bottlenecks and propose improvements to scalability, efficiency, and reliability

Requirements

• Bachelor’s or Master’s degree in CS, AI, Data Science, or related field
• 5+ years of applied AI/NLP/ML engineering, including at least 2 years working directly with LLMs, RAG, semantic search, and Agentic AI
• Deep familiarity with LLMs (e.g., OpenAI, Claude, Gemini) and responsible deployment in production
• Experience designing and optimizing:
  • RAG pipelines
  • semantic search
  • vector databases (e.g., ElasticSearch, Pinecone)
  • agentic / multi-agent AI workflows at scale
• Proficiency with modern ML frameworks/libraries (e.g., LangChain, LlamaIndex, PyTorch, HuggingFace Transformers)
• Hands-on experience in Python and designing APIs / scalable backend services
• Cloud experience building, deploying, and monitoring AI/ML workloads (e.g., AWS, Azure; AWS SageMaker/Bedrock, Azure AI)
• Familiarity with MLOps and CI/CD for AI, including model monitoring and data versioning
• Ability to work with large datasets (data cleaning, feature engineering, scalable data pipelines)
• Strong problem-solving, collaboration, and communication skills; ability to work in remote/distributed teams

Nice to Have

• Exposure to MCP and A2A protocol
• Exposure to GraphRAG / graph-based knowledge retrieval
• Experience using tools to load balance across LLM providers