About the Role
This role is based in Pune, India with a hybrid work model requiring three days per week in the office. It is a full-time individual contributor position, with opportunities available for mid, senior, and principal-level engineers depending on experience and fit.
Responsibilities
- Design and implement complete user experiences by developing responsive front-end interfaces and robust backend microservices.
- Ensure smooth integration between user interfaces and independent backend AI agents.
- Uphold high coding standards, conduct unit testing, and enhance front-end efficiency for intricate enterprise workflows.
- Develop the architecture for multi-phase agent coordination, tool invocation systems, state management logic, and error handling mechanisms.
- Create and refine schemas for the Enterprise Knowledge Graph and manufacturing-specific domain models.
- Manage the design and operation of the LLM Gateway, including model selection, cost controls, response time targets, and real-time data streaming.
- Drive large-scale refactoring of Java applications, improve modularity, and adapt business logic for integration with cloud and AI technologies.
- Transform data architecture by overseeing schema evolution, boosting system performance, and scaling PostgreSQL databases to support downstream AI pipelines.
- Improve system dependability, implement secure sandboxing methods, and advance cloud-native microservices design.
Work Arrangement
Hybrid — Pune, India
Position Overview
- Location: Pune, India (Hybrid: 3 days/week from the office)
- Employment Type: Full-Time, Individual Contributor (IC) Roles
- Experience Levels: Mid, Senior, and Principal levels available depending on track match.
Strict Application Filters
- Notice Period: Maximum 30 days (Immediate joiners strongly preferred). Candidates with a notice period exceeding 30 days will not be considered.
- AI Experience (All Levels): Mandatory production or hands-on exposure to AI architectures for ALL roles. Whether you are a Mid-level developer or a Principal Architect, you must have experience building or integrating applications with LLMs, prompt engineering, vector embeddings, RAG pipelines, or agentic frameworks.
Track A: Full-Stack Product Engineering (Mid to Senior Levels)
- Core Focus: Building feature-rich, high-performance web applications that integrate with backend AI intelligence.
- Key AI Requirements: Experience consumption of streaming AI APIs, orchestrating UI states based on dynamic LLM responses, and building interfaces for AI-driven workflows.
- Key Responsibilities: Engineer end-to-end user journeys, deploying highly interactive frontends and resilient microservices.
- Key Responsibilities: Integrate user interfaces seamlessly with autonomous backend agents.
- Key Responsibilities: Maintain clean code standards, unit testing, and optimize front-end performance for complex enterprise user workflows.
- Tech Stack: Modern JavaScript/TypeScript frameworks (React.js, Angular, or Vue), Node.js/Java backends, RESTful APIs, GraphQL, Microservices.
Track B: Agentic AI & Intelligence Infrastructure (Principal Level)
- Core Focus: Building the runtime orchestration and data models that power our autonomous AI agents.
- Key Responsibilities: Architect the multi-step agent orchestrator, tool dispatch systems, state machines, and error recovery frameworks.
- Key Responsibilities: Design and optimize the Enterprise Knowledge Graph schema and manufacturing domain ontologies.
- Key Responsibilities: Own LLM Gateway architecture: model routing, cost governance, latency SLOs, and streaming responses.
- Tech Stack: LangGraph, AutoGen, Model Context Protocol (MCP), Neo4j, Amazon Neptune, RDF/OWL ontologies, Vector/Graph hybrid search, Distributed Systems.
Track C: Platform Architecture & Modernization (Principal Level)
- Core Focus: High-throughput backend systems, cloud infrastructure scaling, and database evolution optimized for heavy AI workloads.
- Key Responsibilities: Lead enterprise-scale Java application refactoring, modularization, and future-proofing application logic for modern cloud & AI layers.
- Key Responsibilities: Redefine data architecture, manage complex schema migrations, optimize performance, and scale PostgreSQL backends to feed downstream AI data pipelines.
- Key Responsibilities: Enhance infrastructure reliability, sandboxing patterns, and cloud-native microservices architecture.
- Tech Stack: Java/Spring Boot (advanced refactoring), PostgreSQL (expert-level indexing, query tuning, migration), AWS/Cloud-native architectures, Kubernetes, Docker.
Other
Hybrid work: 3 days/week from the office
