AI/ML Lead

Overview We are seeking a highly skilled AI Lead to design, build, and optimize advanced AI systems that leverage Retrieval-Augmented Generation (RAG), multi-modal models, and agentic architectures. The ideal candidate will have deep experience working with large-scale knowledge bases, modern vector search technologies, and hands-on development of production-grade AI features. This role requires a strong blend of engineering, research awareness, and the ability to drive innovation end-to-end. Key Responsibilities • Architect, build, and optimize complex RAG pipelines, supporting multi-domain knowledge bases, high-volume datasets (TB-scale), and advanced chunking/indexing strategies. • Lead and execute multi-modal AI experiments, including image, diagram, and text-based use cases. • Develop and maintain knowledge graph–driven solutions to enhance retrieval, reasoning, and context management. • Design and build agentic AI systems that go beyond conversational interactions to enable task-oriented, autonomous, and tool-augmented agents. • Evaluate and recommend alternative AI/LLM approaches, bringing strong industry awareness of emerging techniques, model capabilities, and best practices. • Define and implement evaluation frameworks (Evals) to measure model performance, quality, safety, and reliability. • Implement observability and monitoring for AI pipelines, including telemetry, tracing, and error detection for LLM-driven workflows. • Work hands-on with OpenAI technologies, APIs, and model ecosystem to build advanced features. • Apply prompt engineering and LLM design patterns to build robust end-to-end AI solutions. • Develop high-quality software using Python, including data processing, model orchestration, and integration layers. • Leverage and optimize vector databases / vector stores for retrieval, semantic search, and scalable indexing. Qualifications • 8+ years of software engineering or applied ML experience. • Proven track record implementing production RAG systems at scale. • Strong understanding of embeddings, vector similarity search, chunking heuristics, and retrieval performance optimization. • Hands-on experience with multi-modal models (e.g., VLMs, OCR, vision-language reasoning). • Experience working with knowledge graphs (Neo4j, RDF, graph embeddings, or similar). • Prior work building agentic/LLM-driven systems (tool use, planning, function calling, agents). • Strong Python engineering skills, including modern tooling and best practices. • Familiarity with AI observability frameworks, experiment tracking, and evaluation tooling. • Experience with OpenAI APIs, or comparable LLM platforms. • Ability to stay current with rapidly evolving AI research and translate advancements into practical solutions. Nice to Have • Experience with distributed systems and high-volume data processing. • Prior experience in ML Ops, GPU orchestration, or model deployment pipelines. • Background in search systems, IR, or NLP.