We are building a new AI engineering team focused on production-grade LLM integrations, AI-powered workflows, intelligent automation, and integration with an existing Java/Spring backend platform.

These roles are hands-on software engineering roles, not primarily ML research roles.

The team's initial focus areas include semantic/hybrid search and retrieval and AI-powered operational automation such as intent-driven workflows, tool calling, customer/operations workflows, and integration with existing services.

Lead AI Engineer :

Experience : 8 - 15 years of professional software engineering experience, with recent hands-on experience building LLM/Generative AI applications.

About the Role :

We are looking for a Lead AI Engineer to lead the architecture, development, and productionization of LLM-powered products, semantic search and retrieval systems, intelligent workflows, and AI-assisted operational automation.

This is a hands-on engineering leadership role. The engineer will remain involved in design and implementation while setting technical direction, establishing engineering practices, mentoring the team, and taking AI solutions from experimentation to reliable production systems.

The role requires strong software engineering and distributed-systems fundamentals combined with practical experience building applications using LLMs, AI APIs, tool calling, RAG, and workflow orchestration.

Key Responsibilities :

- Lead the architecture, development, and productionization of LLM-powered applications and AI workflows.

- Design AI application architectures involving LLMs, tool calling, structured outputs, semantic/hybrid search, RAG, retrieval and ranking, workflow orchestration, and integrations with backend services.

- Build and review production-quality Python services and AI workflows.

- Evaluate and integrate foundation models and LLM APIs based on capability, latency, reliability, privacy, and cost.

- Design reliable agentic and workflow-based systems, including tool execution, state management, retries, fallbacks, guardrails, and human-in-the-loop workflows where appropriate.

- Establish appropriate boundaries between LLM-driven decisions and deterministic application/business logic.

- Work closely with Java backend teams to integrate AI capabilities with existing APIs, services, databases, and event-driven systems.

- Drive technical evaluation and POCs and establish a path for taking successful experiments into production.

- Establish practices for AI application evaluation, testing, observability, security, reliability, and cost management.

- Mentor SDE3 and SDE2 engineers and raise engineering standards across the team.

- Partner with Product, Backend Engineering, Data, and Business teams to identify high-value opportunities for AI automation.

- Own technical architecture and engineering quality for AI initiatives.

Must-Have Skills :

- 8+ years of professional software engineering experience.

- Strong hands-on Python development experience.

- Strong software engineering fundamentals: DSA, OOP, API design, databases, distributed systems, concurrency, testing, and debugging.

- Recent hands-on experience building and deploying applications using LLMs or Generative AI APIs.

- Strong understanding of LLM application patterns including prompt design, structured outputs, tool/function calling, context management, and model selection.

- Hands-on experience designing AI workflows or agentic systems that interact with tools, APIs, or backend services.

- Practical experience with semantic/hybrid search, embeddings, vector search, retrieval/ranking pipelines, and RAG.

- Experience integrating LLM applications with production backend systems.

- Experience designing scalable, reliable, production-ready services.

- Good understanding of Java-based backend systems; familiarity with Spring/Spring Boot strongly preferred.

- Experience with cloud infrastructure and modern deployment practices.

- Experience with Docker, Kubernetes, CI/CD, or equivalent technologies.

- Experience using logs, metrics, traces, and other observability mechanisms to diagnose production systems.

- Ability to make architectural decisions and clearly articulate technical tradeoffs.

Good-to-Have Skills :

- LangGraph, LangChain, LlamaIndex, or equivalent orchestration/retrieval frameworks.

- OpenSearch/Elasticsearch, Pinecone, Weaviate, Milvus, Qdrant, FAISS, or similar search/vector technologies.

- Kafka or other event-driven architectures.

- Experience building evaluation frameworks for LLM applications, search relevance, retrieval quality, or automated AI quality evaluation.

- LLM observability or LLMOps tooling.

- Multimodal AI applications.

- Model fine-tuning, LoRA/PEFT, or model serving.

- AI-assisted software engineering tools.

- High-scale consumer, D2C, e-commerce, marketplace, or operational systems.