Requirements:

• 4+ years of professional experience in software or machine learning engineering, or demonstrable equivalent impact.
• At least 1 year of hands-on experience building and operating production-ready Generative AI/LLM solutions in live products, including the implementation of guardrails, hallucination reduction techniques, and safety mitigations.
• 1+ year of experience in mentoring or technical leadership, including responsibilities such as code reviews, architecture sign-off, and sprint planning/guidance.
• Proven experience developing in Python, along with proficiency in at least one major Generative AI SDK (e.g. OpenAI, Anthropic, Gemini, or Hugging Face Transformers).
• Strong background in integrating and tuning vector databases (such as Pinecone, Weaviate, or FAISS) to support retrieval-augmented generation (RAG) pipelines.
• Comfortable working across web technology stacks (React/HTML/JavaScript), with experience in REST/gRPC APIs, Docker, and Git workflows

Responsibilities: 

• Deliver high-impact GenAI features hands-on: prompt engineering, rapid prototypes, model integrations, and MLOps-lite pipelines.
• Coach 3-5 engineers through pair programming, goal-setting, and career growth.
• Run design and code reviews; uphold secure, well-documented, test-driven practices.
• Chair squad-level design sessions.
• Contribute to the AI Technical Committee reviewing new solution designs and reference architectures.
• Classify GenAI initiatives into low/medium/high risk (e.g., marketing copy vs. compliance automation).
• Shape mitigation plans covering model choice, data privacy, bias, latency, and hallucination.
• Define SLOs for latency, cost, and accuracy; instrument telemetry and alerts.
• Partner with Product Owners, Ops, and Risk to refine requirements and ship safely.