1 day ago
Pune, IndiaStaff+
Responsibilities
- Architect, develop, and operate scalable enterprise knowledge graph platforms, including ingestion, entity extraction, resolution, relationship mapping, ontologies, retrieval, and reasoning.
- Build production AI applications using RAG, GraphRAG, agentic AI, intelligent workflows, and multiple proprietary and open-source LLMs.
- Design model-agnostic architectures with model routing and fallback strategies while optimizing prompts, context, inference performance, token usage, and cost.
- Build LLM evaluation, monitoring, guardrail, observability, distributed tracing, and operational diagnostic capabilities.
- Architect fault-tolerant, cloud-native distributed systems with high-throughput data pipelines, low-latency APIs, secure multi-tenancy, and event-driven components.
- Own the engineering lifecycle from architecture and implementation through deployment, maintenance, incident management, reliability, and performance optimization.
- Provide technical direction across engineering teams, lead architecture reviews and technology evaluations, mentor senior engineers, and make long-term platform decisions.
Requirements
- 10–15+ years of software engineering experience, including significant experience designing and operating large-scale distributed systems.
- Strong proficiency in Python, Java, Go, or equivalent backend programming languages.
- Experience architecting, developing, and maintaining enterprise-scale software platforms and independently driving complex initiatives from design through production.
- Hands-on experience building and deploying knowledge graph or graph-based data systems, including graph databases, graph algorithms, semantic modeling, and knowledge retrieval.
- Practical experience building production AI applications with multiple LLM providers and understanding model-specific capabilities, limitations, and trade-offs.
- Strong understanding of RAG architectures, embeddings, vector databases, and hybrid retrieval.
- Expertise with cloud technologies such as AWS, Azure, or GCP, plus microservices, containers, Kubernetes, APIs, and distributed data processing.
- Strong knowledge of system design, scalability, concurrency, reliability, performance optimization, and secure production operations.
- Preferred experience with Neo4j, Amazon Neptune, RDF, SPARQL, Cypher, Elasticsearch, OpenSearch, Pinecone, Weaviate, Milvus, pgvector, OpenAI, Anthropic Claude, Google Gemini, Llama, Mistral, LangChain, LlamaIndex, LangGraph, Docker, Terraform, Kafka, Redis, and PostgreSQL.
- Experience taking AI applications from experimentation to secure, reliable, cost-efficient production deployments and influencing architecture across multiple teams.
Tech Stack
Apache KafkaAWSAzureDockerElasticsearchGoGoogle Cloud PlatformJavaKubernetesNeo4jPostgreSQLPythonRedisTerraform
Categories
About Showpad
Showpad builds a SaaS platform for revenue enablement that unifies content management, sales readiness and coaching, buyer engagement, and revenue intelligence for enterprise sales and marketing teams, especially in field-driven industries. The company was founded in 2011 and is headquartered in Waltham, Massachusetts. It is privately held and owned by Vector Capital.