Stay up to date with progress in agent development, and implementation techniques.
Design and iterate on novel AI architectures to solve real world tasks.
Build evaluation pipelines to test the agents you implement.
Collaborate closely with product and design teams to iterate on new features and enhance the product roadmap
Drive aggressive project timelines while ensuring high engineering standards are being met by writing clean, maintainable, and well-tested code
Job requirement:
More than 5 years of professional experience in software engineering working on complex platform products including building AI applications professionally.
Experience implementing evaluations for agents/workflows.
A subject matter expert in the components that make up an AI application, and how/when to best utilize each: prompting/context engineering, retrieval methods, agent architecture, LLM inference APIs & what LLMs preform best in specific tasks (e.g. Gemini for multimodal).
Strong coding skills in Python or TypeScript, ideally both.
Experience with API frameworks like FastAPI and/or flask and building high-traffic or mission-critical systems.
Expertise in LangChain/LangGraph.
Demonstrated ability to debug, troubleshoot, and optimize backend services.
Strong written and oral communication skills, with the ability to explain technical concepts clearly and concisely to both technical and non-technical stakeholders.
Knowledge of AWS cloud platforms and their managed services.
