Leads the team this role joins
Decides on early hires
Runs hiring at the company
From your own Gmail and LinkedIn.
About the role
This is a senior software engineering role for someone with six to ten years of experience, and it is listed as remote across India and Asia. The engineer builds Energy Assistant, a GenAI assistant inside utility web portals and mobile apps that answers questions about usage, bills, appliances and savings. The system is a multi-agent design built on LangGraph, and the engineer owns major components, helps shape architecture and mentors SDE1 and SDE2 engineers.
What you’ll do
- Design and build production multi-agent systems, including routing, specialist agents, LangGraph workflows, tool calling, memory and checkpointing.
- Create typed tool contracts and data access layers over internal APIs, so the model explains computed results rather than generating numbers.
- Build RAG pipelines for tariff and knowledge retrieval with tenant-isolated embeddings.
- Manage latency, reliability and cost using caching, retries, circuit breakers and model routing.
- Add guardrails for prompt injection, scope control, authorization and tenant isolation.
- Build observability and evaluation hooks with LangSmith, and work with SDETs on datasets and release criteria.
- Diagnose production agent failures using traces, logs and metrics.
- Support streaming over WebSocket or SSE and widget integration with front-end teams.
- Lead design and code reviews, set engineering standards and mentor engineers.
- Explain designs, trade-offs and progress to engineering, product and leadership.
What they’re looking for
- Six to ten years of software engineering, including one to two years shipping LLM or GenAI features to production.
- Strong Python and working knowledge of Java.
- Hands-on experience with LangChain, LangGraph or similar agent orchestration frameworks.
- Experience with LLM APIs such as OpenAI, Anthropic or Amazon Bedrock, including prompt design, tool calling and structured outputs.
- Experience building RAG systems with embeddings and vector stores such as pgvector.
- Strong backend and API design for scalable, low-latency services.
- Experience with AWS, EKS containers, PostgreSQL, Redis and CI/CD.
- Experience with evals, LLM-as-judge or AI observability tools such as LangSmith.
- Strong system design, analytical and communication skills.
Nice to have
- Time-series, IoT or smart meter data experience, or work in energy and utilities.
- Experience with voice or IVR GenAI products.
- Experience with multi-tenant SaaS, security and data privacy for LLM applications.
Skills
Questions about this role
Is this role remote?
It is listed as remote for India and Asia.
How many years of experience do I need?
Six to ten years of software engineering, including one to two years building LLM or GenAI features in production.
Which frameworks does the team use?
LangGraph, LangChain and LangSmith, with OpenAI, Anthropic or Amazon Bedrock models and pgvector.