Senior AI Engineer — Agents & Automation

About the job

One of our clients is seeking a senior engineer to deliver intelligent assistants and reliable agent-driven business workflows.

Responsibilities

• Build multi-agent systems that reason, plan and execute complex sales workflows.
• Develop assistants that maintain context across multi-turn conversations.
• Create a scalable LLM and agent platform that enables adoption across engineering teams.
• Implement the backend services that support intelligent assistants.
• Deliver conversational experiences, natural-language search and personalized email generation.
• Where relevant, improve search relevance, ranking and recommendation models.
• Where relevant, build entity extraction for company and people data, keyword detection and industry classification.
• Where relevant, develop lookalike matching and suggestion engines.
• Engineer production LLM applications for scalability, reliability, availability and performance.
• Implement multi-step agents that chain model calls, use external APIs and maintain workflow state.
• Optimize prompts and select appropriate prompting, fine-tuning and advanced model techniques.
• Build robust APIs connecting AI capabilities with existing infrastructure and external services.
• Establish evaluation, A/B testing and monitoring for accuracy, safety and reliability.
• Optimize inference cost, latency and scaling across model providers and deployment options.
• Work with product, backend engineering and business teams to define requirements and deliver useful outcomes.

Required Qualifications

• At least eight years of software engineering experience delivering production systems.
• At least 1.5 years of hands-on development with LLM applications using models such as GPT, Claude or Llama.
• A record of delivering scalable customer-facing products used in practice, beyond prototypes or internal demonstrations.
• Experience creating multi-step agents and chaining complex workflows.
• Deep knowledge of prompting, including few-shot techniques, reasoning-oriented prompts and prompt optimization.
• Expert Python skills for production applications.
• Experience with scalable backend APIs and distributed architecture.
• Hands-on familiarity with LangChain, LlamaIndex or comparable frameworks.
• Experience integrating multiple APIs and services.
• Experience deploying AI workloads on AWS, Google Cloud or Azure.
• Experience evaluating AI accuracy, safety and performance rigorously.
• Knowledge of A/B testing and experiment design.
• Ability to instrument, monitor, alert on and debug complex AI systems.
• Experience building scalable supporting data pipelines.
• Ability to design complete backend systems incorporating asynchronous workflows and LLM agents.
• Ability to evaluate the costs and benefits of different AI approaches.
• Sound judgment about model providers, prompting versus fine-tuning, and application architecture.
• Ability to create repeatable evaluations with measurable outcomes.
• A habit of tracking iteration results and explaining why an approach succeeds or fails.
• Attention to safety, reliability and user experience alongside model capability.
• Ongoing familiarity with developments in large language models.
• Ability to adapt to new models, frameworks and techniques.
• Comfort breaking ambiguous, complex problems into executable engineering work.