Position Overview
The Senior AI Engineer reports to the Head of Technology and is responsible for the entire lifecycle of AI solutions, from design to deployment. This includes using multi-agent workflows, advanced knowledge retrieval, and large language models to solve enterprise challenges, thereby improving business efficiency, innovation, and strategic decision-making. The role involves leading projects such as AI Copilots, Enterprise Search Solutions, Summarization Engines, and Intelligent Automation Tools, ensuring they are robust, scalable, and production-ready. A key aspect of the role is mentoring junior AI Engineers and maintaining high engineering standards. This is a full-time hybrid position based in Mumbai.
Key Responsibilities
Core Functional Responsibilities
● Build and deploy agentic systems and multi-agent workflows using frameworks like LangChain, LlamaIndex, and OpenAI SDK.
● Develop RAG pipelines using embeddings and vector databases (., FAISS, Pinecone, Weaviate, Qdrant).
● Fine-tune and optimize LLMs (GPT-4, Claude, LLaMA, Mistral, Gemini) using techniques like LoRA/QLoRA and quantization.
● Ensure solutions are secure and compliant, with guardrails, safe API usage, and PII protection.
● Implement agent monitoring and evaluation with tools like LangSmith or AgentOps to track and improve performance.
● Deliver real-world enterprise use cases such as AI copilots, workflow orchestration, and intelligent search systems.
● Mentor junior AI Engineers, reviewing their work, sharing best practices, and supporting their growth.
● Collaborate with product, data, and DevOps teams to bring AI solutions to production at scale. Demonstrated knowledge of agentic AI frameworks - Practical experience in Small Language Model (SLM) implementation.
Required Skills & Experience
General & Cross-Functional
● Strong knowledge of LLMs and Gen-AI applications, with hands-on experience in fine-tuning and prompt engineering.
● Proven experience in RAG pipelines and working with vector databases.
● Practical expertise in agent frameworks (LangChain, LlamaIndex, etc.) and multi-agent orchestration.
● Ability to deploy and scale models on cloud platforms (AWS, Azure, HuggingFace, etc.).
● Proficiency in Python or similar programming languages.
● Experience with LLMOps (monitoring, evaluation, cost optimization).
● Strong track record of delivering enterprise-grade AI solutions, not just prototypes.
● Familiarity with agent monitoring/debugging tools (LangSmith, AgentOps).
● Experience mentoring or guiding junior engineers in a technical team.
● (Bonus) Experience fine-tuning open-source LLMs or contributing to community projects.
● (Bonus) Exposure to autonomous agent use cases such as research copilots or intelligent task orchestration