Forward Deployed Engineer, AI Agent
Posted 27ds ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
AI Agent Engineer developing and deploying AI agents to tackle real-world challenges at Cresta. Collaborating with customers and engineering teams for innovative AI solutions.
Responsibilities:
- Develop, configure, deploy, and optimize AI agents using Cresta’s AI platform and tools.
- Build AI agent integrations with external systems (APIs, databases, CRMs, etc.) to ensure seamless workflow integration.
- Optimize AI agent performance (e.g. fine-tune prompts and configurations) and troubleshoot issues in complex enterprise environments.
- Collaborate with customers and internal stakeholders to gather technical requirements and translate business needs into AI Agent solutions.
- Conduct interactive demos and present compelling proof-of-concepts to prospective customers, proactively gather feedback, and iteratively refine solutions to meet objectives.
- Define project milestones, create implementation plans, and coordinate execution with internal teams to ensure on-time delivery. Provide a tight feedback loop to our product and engineering teams — identifying gaps, building custom tooling, and influencing the roadmap through real-world deployment learnings.
- Collaborate with PMs to define agent goals, iterate rapidly based on customer feedback, and shape product capabilities that maximize customer ROI.
- Serve as a trusted technical advisor for the customer, guiding best practices for AI agent adoption and usage. Provide technical guidance on AI agent best practices, including architecture design, security considerations, and scalability planning.
Requirements:
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
- 3+ years of experience in software development, AI/ML engineering, or system integration.
- Proficiency in Python and Golang, with the ability to write clean, efficient code.
- Familiarity with AI/ML concepts. Hands-on experience with large language models (LLMs), and prompt engineering techniques are strongly preferred.
- Strong understanding of general AI agent frameworks, function calling, and retrieval-augmented generation (RAG). Hands-on experience of building such a system is strongly preferred.
- Experience with cloud platforms (AWS, GCP, or Azure) and DevOps practices (CI/CD, containerization, monitoring).
- Hands-on experience with integrating systems via APIs, webhooks, and data pipelines.
- Excellent communication and project management skills.
- Ability to use data-driven decision-making, including A/B testing and performance monitoring, to refine solutions.
- You thrive in cross-functional environments, working hand-in-hand with PMs and engineers to turn real customer problems into scalable AI solutions.
Benefits:
- Compensation for this position includes a base salary, equity, and a variety of benefits.




