Job DescriptionWe're supporting a fast-paced team seeking a hands-on AI Engineer to design and deploy scalable Generative AI solutions. This role is ideal for someone with deep experience in LLM-powered applications, agent frameworks, and Google Cloud Platform (GCP) services such as Vertex AI and BigQuery. The work spans applied AI engineering, solution architecture, and cross-functional collaboration to bring business use cases to life.
Key Responsibilities- Design, build, and deploy LLM-powered solutions using frameworks like LangGraph, Agent SDKs (Google, OpenAI, Microsoft), and PydanticAI.
- Architect and implement multi-agent workflows that incorporate search, automation, retrieval, and summarization.
- Build scalable cloud backends using Vertex AI, Cloud Run Functions, BigQuery, and other GCP services.
- Collaborate with cross-functional teams (e.g., architects, consultants, data engineers) to translate business challenges into AI solutions.
- Prototype rapidly, evaluate LLMs (open-source and proprietary), and deploy PoCs with measurable outcomes.
- Monitor agent reliability, improve response quality, and mitigate hallucinations.
- Write clean, testable, and well-documented code.
- Contribute to internal accelerators and help shape the team's agentic development toolkit.
- Stay current on trends in LLMs, orchestrators, vector DBs, and GCP innovations.
Qualifications- 4-7 years of experience in software engineering, ML engineering, or AI product development.
- Strong Python development skills and experience building modular, scalable systems.
- Demonstrated experience with GenAI systems, including RAG pipelines, custom agents, or conversational assistants.
- Hands-on with GCP, especially Vertex AI, BigQuery, Cloud Run Functions, IAM, and Cloud Storage.
- Proficient with agent frameworks such as Agent SDK, LangGraph, CrewAI, LangChain, LlamaIndex, or PydanticAI.
- Solid understanding of LLM system components: prompt engineering, tool use, RAG, tuning.
- Experience working in ambiguous environments and iterating quickly ("fail fast" mindset).
- Strong communicator-able to explain technical trade-offs to non-technical stakeholders and contribute to client demos or working sessions.
- Skilled in requirements gathering and translating business needs into data or AI workflows.
Preferred QualificationsData Science & MLOps:- Experience comparing GenAI with traditional ML approaches (classification, clustering, summarization).
- Background in data wrangling, especially for RAG pipelines or predictive models.
- Experience with DBT and designing analytics-ready datasets (e.g., star schema).
- Familiar with ML orchestration tools (Vertex Pipelines, Airflow, Prefect).
- Knowledge of model monitoring (drift detection, feedback loops) and version control best practices.
Consulting & Delivery:- Familiar with Agile delivery across phases: discovery, PoC, iteration, deployment, sustainment.
- Able to flag implementation risks, estimate effort, and navigate data dependencies.
We're an equal opportunity employer committed to increasing diversity and inclusion in today's workforce. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status. Minorities, women, LGBTQ candidates, and individuals with disabilities are encouraged to apply. If you require an accommodation, please review our accessibility policy and reach out to our accessibility officer with any questions.
