Software Engineer [Multiple Positions Available]

JPMorganChaseJersey City, NJ
Onsite

About The Position

We are seeking a Software Engineer to lead AI-driven conversation management across user interactions. This role involves ensuring reliable and compliant experiences at scale by managing intent detection, context tracking, escalation, and safety controls. You will also be responsible for running structured reviews for design, performance, and scalability, setting technical vision and architectural standards, and driving reference architectures and roadmaps for critical platforms and services. Additionally, you will establish coding standards, code review practices, and documentation norms, communicate architecture decisions to senior leadership, and own design systems and reusable component libraries to accelerate UI delivery and enforce accessibility and performance standards. This position also involves driving talent acquisition initiatives and working with the scrum team to deliver software solutions that meet functional requirements and provide essential customer benefits.

Requirements

  • Designing and developing user interfaces for AI-driven applications including chatbots, virtual assistants, recommendation systems, and NLP applications related to document summarization
  • Implementing parallel and asynchronous programming techniques, including debouncing, throttling, promises, optimized rendering, lazy loading, and memoization
  • Implementing state management using React and Redux in high-concurrency environments
  • Architecting scalable, real-time frontend and backend systems using event-driven architectures and non-blocking I/O principles
  • Troubleshooting and resolving performance bottlenecks in distributed and asynchronous environments across cloud and on-premises infrastructure
  • Designing, implementing, and evaluating Retrieval-Augmented Generation (RAG) architectures for enterprise-scale AI applications, focusing on accuracy, latency, recall, precision, and scalability
  • Developing hybrid search pipelines including document chunking, vector similarity, and context window management
  • Enhancing semantic search and data access efficiency by leveraging dense and sparse retrieval methods using vector databases including FAISS, Milvus, BM25, and ElasticSearch
  • Integrating retrieval systems with generative models to improve grounding, factuality, and context-aware generation in real-time applications
  • Designing custom retrieval pipelines and implementing performance optimization techniques for production environments
  • Developing and deploying multimodal generative AI applications including text, image, audio, and video modalities
  • Creating and managing semantic video retrieval systems for multimedia datasets using indexing techniques
  • Designing and executing queries using APIs, GraphQL, and relational databases including Oracle and Microsoft SQL Server
  • Applying probability, statistics, optimization, and information theory to model development and evaluation
  • Inventing and implementing novel algorithms in generative modeling and retrieval-augmented systems
  • Optimizing and scaling AI models for real-time inference, low-latency deployment, and cost-effective performance in cloud environments including AWS, Azure, and GCP
  • Creating, deploying, and managing GPT-powered applications in environments including the Apple App Store

Responsibilities

  • Lead AI-driven conversation management across user interactions, including intent detection, context tracking, escalation, and safety controls to ensure reliable and compliant experiences at scale.
  • Run structured reviews for design, performance, and scalability.
  • Set technical vision and architectural standards.
  • Drive reference architectures and roadmaps for critical platforms and services.
  • Establish coding standards, code review practices, and documentation norms.
  • Communicate architecture decisions, risks, and status to senior leadership.
  • Own design systems and reusable component libraries to accelerate UI delivery and enforce accessibility and performance standards.
  • Drive talent acquisition initiatives by actively engaging in the recruitment and hiring process.
  • Work with the scrum team to deliver software solutions by providing the essential benefit to the customers and delivering solution to the functional requirements.

Benefits

  • comprehensive health care coverage
  • on-site health and wellness centers
  • a retirement savings plan
  • backup childcare
  • tuition reimbursement
  • mental health support
  • financial coaching
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service