Senior AI Engineer - Generative AI & Agentic AI
About The Position
The Senior AI Engineer will build, deploy, and support enterprise Generative AI applications and AI agents on an existing AI platform. The role requires production experience with Python, FastAPI, LangChain, LangGraph, GCP, and GitHub Actions. The engineer will work with business users, product teams, architects, and engineers to translate requirements into reliable AI solutions; existing team members will support core architecture and platform design. The position is hybrid in New York or Sunrise, Florida, with three days per week at the client office. It is a contract role, and H1B candidates only are specified. Candidates should have 8–10 years of relevant experience, including at least two years developing GenAI/LLM solutions. A bachelor's or master's degree in Computer Science, Engineering, Artificial Intelligence, or a related field is listed. The posting also specifies a camera-on video screening, an explanation of a production GenAI project and the candidate's contributions, and willingness to attend in-person client interview rounds. Submission materials include an updated resume, contact details, location, availability, confirmed rate, confirmation of office availability, and a brief screening summary validating hands-on experience with mandatory technologies. C2C submissions must confirm H1B status before submission.
Requirements
- 8–10 years of relevant experience, including at least 2 years developing GenAI/LLM solutions.
- Strong hands-on Python and FastAPI experience for production backend services and REST APIs.
- Practical experience with LangChain and LangGraph, including tools, stateful workflows, orchestration, and human-in-the-loop patterns.
- Experience delivering enterprise GenAI applications to production, including prompt design, integration, evaluation, and deployment.
- Hands-on experience deploying and operating applications on GCP.
- Experience using GitHub Actions for CI/CD automation.
- Strong communication skills and direct client or business stakeholder interaction.
- Availability to work from the office in New York or Sunrise, Florida, three days per week.
- Willingness to attend in-person client interview rounds.
- H1B candidates only; C2C submissions must confirm H1B status before submission.
- Bachelor’s or Master’s degree in Computer Science, Engineering, Artificial Intelligence, or a related field.
Nice To Haves
- Production RAG experience, including chunking, retrieval, grounding, and evaluation.
- Experience with vector databases and multi-agent frameworks.
- Familiarity with LLMOps, observability, and knowledge graphs.
- Financial services industry experience.
Responsibilities
- Develop production backend services and REST APIs using Python and FastAPI.
- Build LLM chains, tool integrations, and stateful agent workflows using LangChain and LangGraph.
- Implement orchestration, state management, and human-in-the-loop workflows.
- Integrate enterprise data sources, business systems, and APIs into Generative AI applications.
- Design and refine prompts, evaluate output quality, and improve application performance.
- Deploy and operate AI applications on Google Cloud Platform.
- Build and maintain automated build, test, and deployment pipelines using GitHub Actions.
- Support testing, troubleshooting, monitoring, and production improvements.
- Work with stakeholders to clarify requirements, communicate technical decisions, and demonstrate solutions.
- Explain a production Generative AI project, including personal contributions, workflows, integrations, deployment, pipelines, and quality evaluation during screening.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Career Level
Senior
