Platform Engineer III

Job Summary

We are seeking a highly skilled Generative AI Developer to join the AI Store product team as an embedded AI expert within a squad of 7–10 traditional software engineers (backend, frontend, and full-stack developers). This is not a conventional developer role — the ideal candidate will serve as the squad's single point of contact for all things AI and Generative AI: hands-on developer, internal trainer, technical guide, and implementation lead.

Working under the guidance of the Generative AI Architect, the developer will translate architectural decisions into production-grade implementations, uplift team capabilities through training and mentorship, and independently drive the development of complex GenAI and Agentic AI features for enterprise-grade solutions.

Key Responsibilities

• Act as the squad's embedded GenAI expert and single point of contact for all AI/GenAI-related decisions, implementation, and guidance.

• Design, develop, and optimize production-grade GenAI and Agentic AI applications, services, and pipelines in Python.

• Work under the GenAI Architect to interpret architectural blueprints and implement complex GenAI components, ensuring alignment with enterprise standards.

• Integrate Large Language Models (LLMs) — including OpenAI, Azure OpenAI, Hugging Face, Anthropic, and Cohere — into enterprise workflows and products.

• Design and implement Retrieval-Augmented Generation (RAG) pipelines, multi-agent orchestration systems, and Agentic AI flows.

• Build, maintain, and evolve APIs, automation scripts, and AI pipelines on the AIForce platform.

• Train and mentor squad members (backend, frontend, full-stack developers) on GenAI concepts, tools, frameworks, and best practices — enabling the broader team to actively contribute to AI feature development.

• Conduct LLM performance evaluation, prompt optimization, and model fine-tuning as required.

• Champion Safe AI, AI governance, and responsible AI development practices across the squad.

• Monitor, test, and troubleshoot deployed GenAI models and services in production environments.

• Stay current with emerging GenAI frameworks, LLM advances, and industry trends; proactively assess and introduce relevant innovations.

Skill Requirements

• Strong proficiency in Python (3+ years), including experience building production-grade applications.

• Proven hands-on experience with Agentic AI and GenAI frameworks: Lang Chain, Llama Index, Hugging Face Transformers, Auto Gen, CrewAI, or similar.

• Demonstrated experience designing and implementing RAG architectures, vector search pipelines, and multi-agent systems.

• Familiarity with LLM APIs: OpenAI, Azure OpenAI, Anthropic, Cohere, and open-source models.

• Experience with vector databases (e.g., Pinecone, Weaviate, Azure AI Search, FAISS, Chroma).

• Strong knowledge of prompt engineering, chain-of-thought techniques, and LLM evaluation/observability methods.

• Understanding of LLM fine-tuning approaches (RLHF, PEFT, LoRA) — practical experience will be added advantage.

• Knowledge of Safe AI principles, AI security, AI governance frameworks, and responsible AI development practices.

• Hands-on experience with developing AI solutions on any cloud platform

• Solid software engineering fundamentals: Git, CI/CD pipelines, automated testing, API design.

• Effective communication and mentoring skills — able to explain complex AI concepts to non-AI developers clearly.

Other Requirements

• Experience with MLOps tooling (MLflow, Azure ML Pipelines, or equivalent).

• Exposure to multimodal models (vision-language models, speech-to-text integration).

• Prior experience working as an AI champion or tech lead within a cross-functional product team.

• Familiarity with enterprise AI governance and compliance frameworks.