Job Summary
We are seeking a GenAI candidate with 7+ years of experience to build GenAI solutions using LLMs, RAG, and LangChain to address real‑world business problems. Design and implement autonomous agents capable of task planning, decomposition, and tool/API invocation.
Key Responsibilities
- AI Solution Development: Build GenAI solutions using LLMs, RAG, and LangChain to address real‑world business problems.
- Agentic AI Systems: Design and implement autonomous agents capable of task planning, decomposition, and tool/API invocation.
- Backend & Orchestration Services: Develop robust Python‑based services and orchestrators for managing model interactions, task workflows, and contextual data.
- Cloud‑Based Deployment: Deploy and optimize AI models on Azure OpenAI and GCP Vertex AI, ensuring scalability, reliability, and performance.
- API Integration: Integrate OpenAI and other GenAI services into enterprise applications via REST APIs and cloud‑native SDKs.
- Prompt Engineering & Fine‑Tuning: Craft effective prompts and collaborate on model fine‑tuning to align LLMs with domain‑specific tasks.
- Performance Tuning: Optimize latency, cost, and throughput of GenAI models running on cloud platforms.
- Documentation & Knowledge Sharing: Maintain clear documentation and mentor junior team members on GenAI concepts, tools, and best practices.
Required Qualifications
- 7+ years of experience in AI/ML, with at least 3+ years hands‑on in Generative AI / LLM systems.
- Proven expertise in LangChain, OpenAI APIs, Azure OpenAI, and GCP Vertex AI.
- Strong Python programming skills; experience building REST APIs and microservices.
- Deep knowledge of LLM chaining, RAG, agent‑based systems, and task orchestration.
- Experience deploying scalable AI systems in Azure and GCP environments.
- Familiarity with tools like FAISS, Chroma, Pinecone, Weaviate, or other vector stores.