Company Overview
The hiring company is an early-stage technology organization developing AI-powered products for end users. Its engineering team focuses on building reliable, production-ready AI systems by combining large language models, prompt engineering, agent orchestration, and rigorous evaluation. The company emphasizes rapid experimentation, measurable output quality, and close collaboration between product and platform engineering teams.
Job Description
The AI Engineer will own the prompts, agents, evaluations, and pipelines that power user-facing AI features. The role involves translating product requirements into functional AI systems, rigorously testing their performance, refining them for production, and continuously improving their quality after deployment.
Working at the intersection of product development and AI infrastructure, the engineer will determine how AI systems should behave, validate their reliability through measurable results, and deliver features that provide real value to users. The ideal candidate can navigate ambiguous technical challenges, move quickly through experimentation, and distinguish between promising demonstrations and systems that perform reliably in production.
This is a fully in-person position requiring five days per week in the office.
Responsibilities
- Build AI-powered features end to end, from initial prototypes through production deployment.
- Improve AI output quality through prompt engineering, model selection, retrieval techniques, and systematic evaluation.
- Design and execute evaluations that measure actual output quality and identify performance issues.
- Rapidly iterate on prompts, agent architectures, and orchestration strategies.
- Collaborate with product engineering to translate requirements into effective, reliable AI features.
- Work with the AI platform team to integrate features into dependable infrastructure.
- Assess new models, tools, and techniques to improve quality, latency, cost efficiency, and system reliability.
- Maintain and continuously improve AI features after they reach production.
Qualifications
- Hands-on experience building LLM-powered features that have been deployed to real users.
- Production software engineering experience with TypeScript and Node.js, particularly in AWS Lambda, and/or Python.
- Experience working with multiple LLM providers, such as Anthropic, OpenAI, Google Vertex AI, AWS Bedrock, or comparable platforms.
- Practical expertise in prompt engineering, retrieval, and agent design, supported by evaluation results.
- Demonstrated experience building evaluation systems capable of detecting regressions.
- Strong software engineering fundamentals, including the ability to write and maintain production-quality code beyond experimental notebooks.
- Ability to work effectively through ambiguous AI problems while balancing speed, quality, and reliability.
Preferred Qualifications
- Experience with provider-abstraction libraries for workflows involving multiple LLM providers.
- Familiarity with pgvector or other vector retrieval systems.
- Experience with model post-training or fine-tuning.
- Experience deploying AI features using AWS Lambda, Amazon ECS Fargate, or similar infrastructure.
- Background in machine learning, natural language processing, or applied research.
- Experience with structured outputs, function calling, and tool use at scale.
- Familiarity with Anyscale Ray or similar distributed computing frameworks for batch inference, evaluation pipelines, or scaling agent workloads.
- Open-source contributions related to LLMs or agent development tools.
Disclaimer
SpringCube curates tech job listings from various company websites to support tech professionals globally.
- No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.
- No Client Relationship: This company is not a client of SpringCube unless stated.
- To Apply: Click the “Apply” button to be redirected to the hiring company’s application page for this job.
- No Liability: SpringCube is not liable for inaccuracies.