Lead Artificial Intelligence/Machine Learning Engineer - LLM

Description :

About the Role :

We are seeking a highly experienced Lead ML Engineer / Senior ML Engineer who will form the core engineering heart of our Intelligence Platform. This role is for someone who thrives in building sophisticated AI systems not just prototypes, but production-grade engines that power real products.

You will be responsible for architecting and implementing the fundamental components of our next-generation AI platform, including agentic workflows, LLM orchestration layers, RAG pipelines, vector retrieval infrastructure, evaluation systems, and scalable ML components that future apps and capabilities will be built upon.

This is a hands-on, high-impact, end-to-end engineering role suited for someone who understands the complexity of AI systems and can design, ship, and scale them in production.

Key Outcomes / Responsibilities :

Core Platform & Architecture :

- Architect and build the core Intelligence Platform that enables agentic behavior, advanced retrieval, and LLM-driven workflows

- Design and implement multi-agent and multi-step reasoning workflows

- Build robust LLM orchestration layers capable of managing prompts, tools, memory, and context

- Own the RAG architecture, including chunking strategies, retrieval optimization, embeddings, and ranking pipelines

Vector Retrieval & Infrastructure :

- Design and implement high-performance vector search and retrieval systems

- Work with vector databases (FAISS, Pinecone, Milvus, Weaviate, LanceDB)

- Optimize embeddings, indexing strategies, and retrieval latency

Evaluation, Monitoring & Observability :

- Establish LLM evaluation frameworks using telemetry, signals, and human feedback

- Build automated evaluation pipelines for quality, accuracy, latency, and reliability

- Instrument end-to-end monitoring for ML systems in production

Engineering Excellence :

- Deliver complex systems from 0 1 scale, not just proofs-of-concept

- Own the full lifecycle : architecture, coding, deployment, performance tuning

- Collaborate with backend, product, and platform teams to build cohesive, scalable systems

Leadership & Collaboration :

- Mentor ML engineers; review designs and code for quality and scalability

- Work cross-functionally with product, PMs, and designers to define use cases

- Drive best practices in RAG, LLM engineering, and AI system design

Required Skills & Experience

Technical Expertise

- 5 - 10 years of experience in Machine Learning / Applied AI

Deep hands-on experience with :

- LLMs, GenAI models, prompt engineering

- RAG systems, retrieval pipelines, hybrid search

- Agentic AI workflows (LangChain, AutoGen, LlamaIndex, DSPy, custom frameworks)

- Embeddings (HuggingFace, OpenAI, Sentence Transformers)

- Vector DBs (FAISS, Pinecone, Milvus, Weaviate, LanceDB)

Strong expertise in :

- Python (production-grade code)

- Systems design & distributed architecture

- Writing optimized and scalable ML backend components

Platform & MLOps :

- Experience deploying AI/ML systems into production environments

- Familiarity with Docker, Kubernetes, cloud (AWS/GCP/Azure)

- Experience with evaluation frameworks, monitoring, and experiment tracking

Software Engineering Skills :

- Strong attention to software complexity, clean architecture, and modular design

- Proven ability to ship complex, multi-component systems

- Ability to debug and optimize both ML pipelines and software infrastructure

Nice-to-Have :

- Experience with RLHF, reward modeling, or ranking systems

- Contributions to open-source LLM/RAG/agentic projects

- Experience building developer tools, AI APIs, or platform-level systems

- A technical leader who can balance innovation with production rigor

- A builder who prefers strong architecture over quick hacks

- Someone who thinks in systems, pipelines, components, and orchestration

- Comfortable with ambiguity and thrilled to build foundational AI infrastructure

- Passionate about agentic systems, autonomous workflows, and the future of AI-driven engineering

Why Join Us?

- Build the core engine that future AI applications will be built upon

- Work on cutting-edge LLM, RAG, and agentic AI challenges

- High ownership, high visibility, and deep technical problem-solving

- A culture rooted in engineering excellence, autonomy, and innovation

Location : Bangalore / Mumbai

Experience : 5 -10 Years

Function : AI/ML Engineering Intelligence Platform