Senior Gen AI Software Engineer
| Company | Liftoff |
|---|---|
| Location | Washington, USA, Oregon, USA, California, USA, Texas, USA, Jackson Township, NJ, USA, Florida, USA, Nevada, USA, Georgia, USA, Minnesota, USA, Colorado, USA, Utah, USA, New York, NY, USA, Massachusetts, USA, Missouri, USA, Michigan, USA, Illinois, USA, Idaho, USA |
| Salary | $140000 – $227000 |
| Type | Full-Time |
| Degrees | |
| Experience Level | Senior, Expert or higher |
Requirements
- Proven experience building products 0-1
- Strong proficiency in Python
- Experience building autonomous Gen AI agents in sales, customer support, or other key functions
- Experience in developing and implementing evaluation frameworks for Gen AI products, including automated testing and human-in-the-loop feedback systems
- Experience as a prompt engineer optimizing Gen AI products through systematic experimentation and iteration
- Ability to navigate ambiguity, make quick, informed decisions, and course-correct rapidly as new information emerges
- Deep understanding of LLMs’ capabilities and advocacy for letting models shine rather than over-constraining them with deterministic prompting
- Strong communication skills to convey complex technical concepts clearly and work effectively with diverse stakeholders
- Lifelong learner with flexible beliefs, thriving on giving and receiving constructive feedback
Responsibilities
- Architect scalable, interoperable AI agents that reimagine and automate workflows across sales, customer success, creative, finance and other core functions
- Rapidly prototype and validate Gen AI solutions through quick proof-of-concepts, then leverage learnings and feedback to ship production-ready solutions at speed
- Partner with decision makers and subject matter experts across the organization to deeply understand existing workflows and seamlessly integrate AI agents into daily operations
- Design robust systems that effectively manage uncertain AI-generated results, create reliable guardrails, and develop flexible products capable of handling the inherent variability in generative AI outputs
- Design and implement comprehensive evaluation frameworks, monitoring systems, and dashboards to assess model performance
- Treat prompt engineering as both an art and a science via iteration, analysis, and collaboration with cross-functional teams to translate human workflows into LLM instructions
- Implement and refine advanced Retrieval-Augmented Generation (RAG) systems, optimizing embedding models, text chunking, and vector storage
- Drive innovation by researching LLM and Generative AI advancements, sharing insights, and proposing new product initiatives that leverage emerging AI capabilities
- Mentor and champion best practices across the engineering team, fostering an environment of open feedback and shared learning that pushes our team forward
Preferred Qualifications
-
No preferred qualifications provided.