Software Engineer 3 - GenAI
About The Position
Bidgely is seeking a senior software engineer to build and scale Energy Assistant, a GenAI assistant embedded in utility web portals and mobile apps. The assistant answers customer questions about energy usage, bills, appliances, rate plans, and savings using a multi-agent system built on LangGraph, Bidgely energy data, tool calls, and deterministic calculations. The engineer will own major components end to end, contribute to architecture, and strengthen the team's engineering standards. This hands-on role involves close collaboration with GenAI engineering, platform, QA/SDET, and product teams. The work includes developing production agent systems and retrieval pipelines, improving latency, reliability, and cost, implementing security and safety controls, and building observability and evaluation capabilities. The role also includes production debugging, supporting streaming and widget integration, leading design and code reviews, mentoring junior engineers, and communicating designs and progress to stakeholders.
Requirements
- 6–10 years of software engineering experience, including at least 1–2 years building and shipping LLM or GenAI features in production.
- Strong Python skills and good 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; prompt design; tool/function calling; and structured outputs.
- Experience building RAG systems with embeddings and vector stores, such as pgvector.
- Strong backend and API design skills, with experience building scalable, low-latency services.
- Experience with AWS, containers (EKS), 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 Haves
- Experience with time-series, IoT, or smart meter data, or the energy and utilities domain.
- Experience with voice or IVR GenAI products.
- Experience with multi-tenant SaaS solutions, security, and data-privacy enhancements for LLM applications.
Responsibilities
- Design and build production multi-agent systems, including supervisor/router and specialist agents, LangGraph workflows, tool calling, conversation memory, and checkpointing.
- Build typed tool contracts and data-access layers over Bidgely APIs so that the LLM explains results rather than generating numbers.
- Develop RAG pipelines for utility tariff and knowledge retrieval, with tenant-isolated embeddings and retrieval.
- Manage latency, reliability, and cost through caching, prewarming, retries, circuit breakers, and model routing across small and large model tiers.
- Implement guardrails for prompt injection, scope control, authorization, tenant isolation, and data management.
- Build observability and evaluation hooks with LangSmith, and collaborate with SDETs on evaluation datasets, regression suites, and release criteria.
- Debug agent failures in production using traces, logs, and metrics, and drive root-cause fixes.
- Support streaming through WebSocket/SSE and widget integration with front-end teams.
- Lead design and code reviews, set engineering standards, and mentor SDE1 and SDE2 engineers.
- Communicate designs, trade-offs, and progress to engineering, product, and leadership.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
