[Hiring] Senior AI Engineer @Trigent Software

Role Description

We are seeking an AI Engineer to design, build, and evolve agent-based AI solutions that leverage large language models (LLMs) to solve business problems. This role focuses on agent architecture, orchestration, retrieval-augmented generation (RAG), and memory management, while partnering with Platform and Data teams for infrastructure, deployment, and integrations. This is a hands-on engineering role centered on production-ready AI workflows, not research or model training.

Key Responsibilities

• Design and implement agentic AI workflows using Python
• Develop AI services and pipelines
• Define and implement agent architecture patterns (planning, tool usage, orchestration, memory)
• Integrate and invoke foundation models via AWS Bedrock
• Optimize LLM behavior through prompt engineering, configuration, and response tuning
• Design and implement Retrieval-Augmented Generation (RAG) solutions
• Integrate and manage vector databases for semantic search and retrieval
• Implement memory and state management using Redis and other persistence mechanisms
• Collaborate with Platform Engineering on deployment, scaling, and security
• Partner with Data and API teams to integrate AI workflows with enterprise data sources
• Evaluate AI outputs and continuously improve accuracy, reliability, latency, and cost
• Document AI patterns, architectures, and best practices

Qualifications

• Strong hands-on experience with Python
• Experience building agent-based AI systems using LangGraph and/or LangFlow
• Solid understanding of agent architecture concepts (tool calling, planning, memory, orchestration)
• Experience integrating and invoking LLMs via AWS Bedrock
• Hands-on experience with LLM tuning through prompts, parameters, and workflows
• Familiarity with vector databases (e.g., OpenSearch, Pinecone, FAISS, or similar)
• Experience with Redis or similar systems for caching and memory management
• Ability to translate business problems into reliable AI solutions

Requirements

• Experience with multi-agent systems and advanced orchestration patterns
• Familiarity with AI evaluation, observability, and monitoring tools
• Experience deploying AI workloads in cloud or Kubernetes environments (in partnership with platform teams)
• Knowledge of data preparation, embedding strategies, and chunking techniques
• Experience working in regulated or enterprise environments