Job Title: Software Development Engineer (Agentic & LLM Commerce Platform)
Location: Bangalore (Hybrid)
Department: Engineering
Employment Type: Full-time
About the Role
We are looking for a highly experienced Software Development Engineer to help build and enhance our next-generation agentic and LLM-powered commerce platform. In this role, you will architect and implement large-scale data and retrieval systems, build custom partner integrations, and develop AI-driven commerce experiences — from semantic product discovery to autonomous, agent-driven purchasing and decisioning workflows used by global brands.
You'll collaborate with product, data science, and client engineering teams to design retrieval-augmented generation (RAG) pipelines, vector search infrastructure, and tool-using agents that power conversational and automated commerce at scale — across millions of transactions and interactions daily.
Key Responsibilities
- Design, develop, and maintain high-scale data ingestion, transformation, and real-time decisioning systems that feed LLM and agentic commerce workflows.
- Build and own semantic search and retrieval infrastructure — including vector databases, embedding pipelines, and hybrid (keyword + semantic) search — powering product discovery and contextual recommendations.
- Architect retrieval-augmented generation (RAG) systems and orchestrate tool-using AI agents that can reason over catalogs, execute multi-step commerce tasks, and act autonomously on behalf of users.
- Build and own custom integrations with commerce platforms, payment and checkout providers, CDPs, analytics platforms, and customer data APIs.
- Improve performance of real-time commerce workflows such as conversational search, dynamic content retrieval, intent understanding, and agentic order orchestration.
- Write clean, maintainable, and well-tested code across backend services, data pipelines, and model-serving components.
- Partner with data science teams to productionize LLMs and machine learning models, including embedding generation, feature engineering, evaluation, and model-serving components.
- Ensure reliability and low latency across distributed systems processing large volumes of events and inference requests in real time.
- Mentor engineers, lead design reviews, and drive engineering best practices.
- Contribute to continuous improvement in observability, evaluation/guardrails for LLM systems, CI/CD, and deployment automation.
Required Qualifications
- 1+ years of professional software engineering experience, ideally in commerce, AI/ML, or other data-intensive environments.
- Strong proficiency in backend languages such as Java, Scala, or Python.
- Hands-on experience building AI-powered features using LLMs — including prompt engineering, RAG, embeddings, or agentic / tool-calling frameworks.
- Experience with semantic / vector search and vector databases (e.g., Pinecone, Weaviate, Milvus, pgvector, FAISS, or OpenSearch/Elasticsearch vector capabilities) and embedding models.
- Experience with large-scale data processing using technologies like Kafka, Spark, Flink, Beam, or similar.
- Hands-on experience with REST/GraphQL APIs, webhooks, OAuth flows, and partner integration frameworks.
- Strong understanding of distributed systems, caching, message queues, and low-latency architectures.
- Experience with SQL and NoSQL databases for storing high-volume datasets.
- Familiarity with cloud platforms (AWS, GCP, or Azure) and container orchestration (Docker, Kubernetes).
- Solid understanding of algorithms, data structures, and system design.
Preferred Qualifications
- Experience building agentic systems — multi-agent orchestration, tool/function calling, planning, or autonomous workflows (e.g., LangChain, LlamaIndex, LangGraph, or custom frameworks).
- Deep experience with retrieval pipelines: chunking strategies, hybrid search, re-ranking, and relevance tuning for semantic search.
- Knowledge of the machine learning lifecycle, model deployment, feature stores, real-time inferencing, and LLM evaluation / observability.
- Experience in the commerce ecosystem: product catalogs, recommendation systems, checkout/payment flows, identity, event pipelines, or attribution systems.
- Familiarity with privacy compliance (GDPR, CCPA) and secure customer data handling, including responsible AI and data governance for LLM systems.
- Experience optimizing inference cost and latency (caching, batching, model routing, quantization, or serving frameworks).
- Strong communication skills and ability to collaborate across product, engineering, and client-facing teams.
What We Offer
- Competitive compensation and benefits
- Opportunity to build impactful AI technology used by global brands
- Work in an innovative, AI-forward agentic commerce environment
- Flexible, hybrid, or remote work options
- Growth opportunities in a fast-moving and hig
